人脸识别论文文献翻译中英文

合集下载

人脸识别论文文献翻译中英文

人脸识别论文文献翻译中英文人脸识别论文中英文附录(原文及译文)翻译原文来自Thomas David Heseltine BSc. Hons. The University of YorkDepartment of Computer ScienceFor the Qualification of PhD. -- September 2005 -《Face Recognition: Two-Dimensional and Three-Dimensional Techniques》4 Two-dimensional Face Recognition4.1 Feature LocalizationBefore discussing the methods of comparing two facial images we now take a brief look at some at the preliminary processes of facial feature alignment. This process typically consists of two stages: face detection and eye localisation. Depending on the application, if the position of the face within the image is known beforehand (for a cooperative subject in a door access system for example) then the face detection stage can often be skipped, as the region of interest is already known. Therefore, we discuss eye localisation here, with a brief discussion of face detection in the literature review(section 3.1.1).The eye localisation method is used to align the 2D face images of the various test sets used throughout this section. However, to ensure that all results presented arerepresentative of the face recognition accuracy and not a product of the performance of the eye localisation routine, all image alignments are manually checked and any errors corrected, prior to testing and evaluation.We detect the position of the eyes within an image using a simple template based method. A training set of manually pre-aligned images of faces is taken, and each image cropped to an area around both eyes. The average image is calculated and used as a template.Figure 4-1 - The average eyes. Used as a template for eye detection.Both eyes are included in a single template, rather thanindividually searching for each eye in turn, as the characteristic symmetry of the eyes either side of the nose, provides a useful feature that helps distinguish between the eyes and other false positives that may be picked up in the background. Although this method is highly susceptible to scale(i.e. subject distance from thecamera) and also introduces the assumption that eyes in the image appear near horizontal. Some preliminary experimentation also reveals that it is advantageous to include the area of skin just beneath the eyes. The reason being that in some cases the eyebrows can closely match the template, particularly if there are shadows in the eye-sockets, but the area of skin below the eyes helps to distinguish the eyes from eyebrows (the area just below the eyebrows contain eyes, whereas the area below the eyes contains only plain skin).A window is passed over the test images and the absolute difference taken to that of the average eye image shown above. The area of the image with the lowest difference is taken as the region of interest containing the eyes. Applying the same procedure using a smallertemplate of the individual left and right eyes then refines each eye position.This basic template-based method of eye localisation, although providing fairly preciselocalisations, often fails to locate the eyes completely. However, we are able to improve performance by including a weighting scheme.Eye localisation is performed on the set of training images, whichis then separated into two sets: those in which eye detection was successful; and those in which eye detection failed. Taking the set of successful localisations we compute the average distance from the eye template (Figure 4-2 top). Note that the image is quite dark, indicating that the detected eyes correlate closely to the eye template, as wewould expect. However, bright points do occur near the whites of the eye, suggesting that this area is often inconsistent, varying greatly fromthe average eye template.Figure 4-2 – Distance to the eye template for successful detections (top) indicating variance due tonoise and failed detections (bottom) showing credible variance dueto miss-detected features.In the lower image (Figure 4-2 bottom), we have taken the set of failed localisations(images of the forehead, nose, cheeks, background etc. falsely detected by the localisation routine) and once again computed the average distance from the eye template. The bright pupils surrounded by darker areas indicate that a failed match is often due to the high correlation of the nose and cheekbone regions overwhelming the poorly correlated pupils. Wanting to emphasise the2difference of the pupil regions for these failed matches and minimise the variance of the whites of the eyes for successful matches, we divide the lower image values by the upper image to produce a weights vector as shown in Figure 4-3. When applied to the difference image before summing a total error, this weighting scheme provides a much improved detection rate.Figure 4-3 - Eye template weights used to give higher priority to those pixels that best represent the eyes.4.2 The Direct Correlation ApproachWe begin our investigation into face recognition with perhaps the simplest approach,known as the direct correlation method (also referred to as template matching by Brunelli and Poggio [ 29 ]) involving the direct comparison of pixel intensity values taken from facial images. We use the term ‘Direct Correlation’ to encompass all techniques in which face images are compared directly, without any form of image spaceanalysis, weighting schemes or feature extraction, regardless of the distance metric used. Therefore, we do not infer that Pearson’s correlation is applied as the similarity function (although such an approach would obviously come under our definition of direct correlation). We typically use the Euclidean distance as our metric in these investigations (inversely related to Pearson’s correlation and can be considered as a scale and translation sensitive form of image correlation), as this persists with the contrast made between image space and subspace approaches in later sections.Firstly, all facial images must be aligned such that the eye centres are located at two specified pixel coordinates and the image cropped to remove any backgroundinformation. These images are stored as greyscale bitmaps of 65 by 82 pixels and prior to recognition converted into a vector of 5330 elements (each element containing the corresponding pixel intensity value). Each corresponding vector can be thought of as describing a point within a 5330 dimensional image space. This simple principle can easily be extended to much larger images: a 256 by 256 pixel image occupies a single point in 65,536-dimensional image space and again, similar images occupy close points within that space. Likewise, similar faces are located close together within the image space, while dissimilar faces are spaced far apart. Calculating the Euclidean distance d, between two facial image vectors (often referred to as thequery image q, and gallery image g), we get an indication of similarity. A threshold is thenapplied to make the final verification decision.d q g (d threshold ?accept d threshold ?reject ) . Equ. 4-134.2.1 Verification TestsThe primary concern in any face recognition system is its ability to correctly verify a claimed identity or determine a person's most likely identity from a set of potential matches in a database. In order to assess a given system’s ability to perform these tasks, a variety of evaluation methodologies have arisen. Some of these analysis methods simulate a specific mode of operation (i.e. secure site access or surveillance), while others provide a more mathematical description of data distribution in someclassification space. In addition, the results generated from each analysis method may be presented in a variety of formats. Throughout the experimentations in this thesis, we primarily use the verification test as our method of analysis and comparison, although we also use Fisher’s Linear Discriminant to analyse individual subspace components in section 7 and the identification test for the final evaluations described in section 8. The verification test measures a system’s ability to correctly accept or reject the proposed identity of an individual. At a functional level, this reduces to two images being presented forcomparison, for which the system must return either an acceptance (the two images are of the same person) or rejection (the two images are of different people). The test is designed to simulate the application area of secure site access. In this scenario, a subject will present some form of identification at a point of entry, perhaps as a swipe card, proximity chip or PIN number. This number is then used to retrieve a stored image from a database of known subjects (often referred to as the target or gallery image) and compared with a live image captured at the point of entry (the query image). Access is then granted depending on the acceptance/rejection decision.The results of the test are calculated according to how many times the accept/reject decision is made correctly. In order to execute this test we must first define our test set of face images. Although the number of images in the test set does not affect the results produced (as the error rates are specified as percentages of image comparisons), it is important to ensure that the test set is sufficiently large such that statistical anomalies become insignificant (for example, a couple of badly aligned images matching well). Also, the type of images (high variation in lighting, partial occlusions etc.) will significantly alter the results of the test. Therefore, in order to compare multiple face recognition systems, they must be applied to the same test set.However, it should also be noted that if the results are to be representative of system performance in a real world situation, then the test data should be captured under precisely the same circumstances asin the application environment.On the other hand, if the purpose of the experimentation is to evaluate and improve a method of face recognition, which may be applied to a range of application environments, then the test data should present the range of difficulties that are to be overcome. This may mean including a greater percentage of ‘difficult’ images than4would be expected in the perceived operating conditions and hence higher error rates in the results produced. Below we provide the algorithm for executing the verification test. The algorithm is applied to a single test set of face images, using a single function call to the face recognition algorithm: CompareFaces(FaceA, FaceB). This call is used to compare two facial images, returning a distance score indicating how dissimilar the two face images are: the lower the score the more similar the two face images. Ideally, images of the same face should produce low scores, while images of different faces should produce high scores.Every image is compared with every other image, no image is compared with itself and no pair is compared more than once (we assume that the relationship is symmetrical). Once two images have been compared, producing a similarity score, the ground-truth is used to determine if the images are of the same person or different people. In practicaltests this information is often encapsulated as part of the image filename (by means of a unique person identifier). Scores are thenstored in one of two lists: a list containing scores produced by comparing images of different people and a list containing scores produced by comparing images of the same person. The finalacceptance/rejection decision is made by application of a threshold. Any incorrect decision is recorded as either a false acceptance or false rejection. The false rejection rate (FRR) is calculated as the percentage of scores from the same people that were classified as rejections. The false acceptance rate (FAR) is calculated as the percentage of scores from different people that were classified as acceptances.For IndexA = 0 to length(TestSet)For IndexB = IndexA+1 to length(TestSet)Score = CompareFaces(TestSet[IndexA], TestSet[IndexB])If IndexA and IndexB are the same personAppend Score to AcceptScoresListElseAppend Score to RejectScoresListFor Threshold = Minimum Score to Maximum Score:FalseAcceptCount, FalseRejectCount = 0For each Score in RejectScoresListIf Score <= ThresholdIncrease FalseAcceptCountFor each Score in AcceptScoresListIf Score > ThresholdIncrease FalseRejectCount5FalseAcceptRate = FalseAcceptCount / Length(AcceptScoresList)FalseRejectRate = FalseRejectCount / length(RejectScoresList)Add plot to error curve at (FalseRejectRate, FalseAcceptRate)These two error rates express the inadequacies of the system when operating at a specific threshold value. Ideally, both these figures should be zero, but in reality reducing either the FAR or FRR (by altering the threshold value) will inevitably result in increasing the other. Therefore, in order to describe the full operating range of a particular system, we vary the threshold value through the entire range of scores produced. The application of each threshold value produces an additional FAR, FRR pair, which when plotted on a graph produces the error rate curve shown below.6Figure 4-5 - Example Error Rate Curve produced by the verification test.The equal error rate (EER) can be seen as the point at which FAR is equal to FRR. This EER value is often used as a single figure representing the general recognition performance of a biometric system and allows for easy visual comparison of multiple methods. However, it is important to note that the EER does not indicate the level of error that would be expected in a real world application. It is unlikely that any real system would use a threshold value such that the percentage of false acceptances were equal to the percentage of false rejections. Secure site access systems would typically set the threshold such that false acceptances were significantly lower than false rejections: unwilling to tolerate intruders at the cost of inconvenient access denials. Surveillance systems on the other hand would require low false rejection rates to successfully identify people in a less controlled environment. Therefore we should bear in mind that a system with a lower EER might not necessarily be the better performer towards the extremes of its operating capability.There is a strong connection between the above graph and thereceiver operating characteristic (ROC) curves, also used in such experiments. Both graphs are simply two visualisations of the same results, in that the ROC format uses the True Acceptance Rate(TAR), where TAR = 1.0 – FRR in place of the FRR, effectively flipping thegraph vertically. Another visualisation of the verification test results is to display both the FRR and FAR as functions of the threshold value. This presentation format provides a reference to determine the threshold value necessary to achieve a specific FRR and FAR. The EER can be seen as the point where the two curves intersect.7Figure 4-6 - Example error rate curve as a function of the score thresholdThe fluctuation of these error curves due to noise and other errors is dependant on the number of face image comparisons made to generate the data. A small dataset that only allows for a small number of comparisons will results in a jagged curve, in which large steps correspond to the influence of a single image on a high proportion of thecomparisons made. A typical dataset of 720 images (as used insection 4.2.2) provides 258,840 verification operations, hence a drop of 1% EER represents an additional 2588 correct decisions, whereas the quality of a single image could cause the EER tofluctuate by up to 0.28.4.2.2 ResultsAs a simple experiment to test the direct correlation method, we apply the technique described above to a test set of 720 images of 60 different people, taken from the AR Face Database [ 39 ]. Every image is compared with every other image in the test set to produce a likeness score, providing 258,840 verification operations from which to calculate false acceptance rates and false rejection rates. The error curve produced is shown in Figure 4-7.Figure 4-7 - Error rate curve produced by the direct correlation method using no image preprocessing.We see that an EER of 25.1% is produced, meaning that at the EER threshold8approximately one quarter of all verification operations carried out resulted in an incorrect classification. There are a number of well-known reasons for this poor level of accuracy. Tiny changes in lighting, expression or head orientation cause the location in image space to change dramatically. Images in face space are moved far apart due to these image capture conditions, despite being of the same person’s face. The distance between images of different people becomes smaller than the area of face space covered by images of the same person and hence false acceptances and false rejections occur frequently. Other disadvantages include the large amount of storage necessary for holding many face images and the intensive processing required for each comparison, making this method unsuitable for applications applied to a large database. In section 4.3 we explore the eigenface method, which attempts to address some of these issues.4 二维人脸识别4.1 功能定位在讨论比较两个人脸图像，我们现在就简要介绍的方法一些在人脸特征的初步调整过程。

人脸识别论文文献翻译中英文_大学论文

人脸识别论文中英文附录(原文及译文)翻译原文来自Thomas David Heselt ine BSc. Hons. The Un iversity of YorkDepartme nt of Computer Scie neeFor the Qualification of PhD. -- September 2005 -《Face Recog niti on: Two-Dime nsio nal and Three-Dime nsional Tech nique》4 Two-dimensional Face Recognition4.1 Feature LocalizationBefore discuss ing the methods of compari ng two facial images we now take a brief look at some at the prelimi nary processes of facial feature alig nment. This process typically con sists of two stages: face detect ion and eye localisati on. Depe nding on the applicati on, if the positi on of the face with in the image is known beforeha nd (for a cooperative subject in a door access system for example) the n the face detect ion stage can ofte n be skipped, as the regi on of in terest is already known. Therefore, we discuss eye localisati on here, with a brief discussi on of face detect ion in the literature review(sect ion 3.1.1).The eye localisati on method is used to alig n the 2D face images of the various test sets used throughout this section. However, to ensure that all results presented are represe ntative of the face recog niti on accuracy and not a product of the performa nee of the eye localisati on rout ine, all image alig nments are manu ally checked and any errors corrected, prior to testi ng and evaluati on.We detect the position of the eyes within an image using a simple template based method. A training set of manually pre-aligned images of faces is taken, and each image cropped to an area around both eyes. The average image is calculated and used as a template.Figure 4-1 - The average eyes. Used as a template for eye detection.Both eyes are in cluded in a sin gle template, rather tha n in dividually search ing for each eye in turn, as the characteristic symmetry of the eyes either side of the no se, provides a useful feature that helps disti nguish betwee n the eyes and other false positives that may be picked up in the background. Although this method is highly susceptible to scale(i.e. subject distance from the camera) and also in troduces the assumpti on that eyes in the image appear n ear horiz on tai. Some preliminary experimentation also reveals that it is advantageous to include the area of skin just ben eath the eyes. The reas on being that in some cases the eyebrows can closely match the template, particularly if thereare shadows in the eye-sockets, but the area of skin below the eyes helps to disti nguish the eyes from eyebrows (the area just below the eyebrows con tai n eyes, whereas the area below the eyes contains only plain skin).A window is passed over the test images and the absolute difference taken to that of the average eye image shown above. The area of the image with the lowest difference is taken as the region of interest containing the eyes. Applying the same procedure using a smaller template of the in dividual left and right eyes the n refi nes each eye positi on.This basic template-based method of eye localisati on, although provid ing fairly preciselocalisati ons, ofte n fails to locate the eyes completely. However, we are able to improve performa nce by in cludi ng a weighti ng scheme.Eye localisati on is performed on the set of training images, which is the n separated in to two sets: those in which eye detect ion was successful; and those in which eye detect ion failed. Taking the set of successful localisatio ns we compute the average dista nce from the eye template (Figure 4-2 top). Note that the image is quite dark, indicating that the detected eyes correlate closely to the eye template, as we would expect. However, bright points do occur near the whites of the eye, suggesting that this area is often inconsistent, varying greatly from the average eye template.Figure 4-2 -Distance to the eye template for successful detections (top) indicating variance due to noise and failed detections (bottom) showing credible variance due to miss-detected features.In the lower image (Figure 4-2 bottom), we have take n the set of failed localisati on s(images of the forehead, no se, cheeks, backgro und etc. falsely detected by the localisati on routi ne) and once aga in computed the average dista nce from the eye template. The bright pupils surr oun ded by darker areas in dicate that a failed match is ofte n due to the high correlati on of the nose and cheekb one regi ons overwhel ming the poorly correlated pupils. Wanting to emphasise the differenee of the pupil regions for these failed matches and minimise the varianee of the whites of the eyes for successful matches, we divide the lower image values by the upper image to produce a weights vector as show n in Figure 4-3. When applied to the differe nee image before summi ng a total error, this weight ing scheme provides a much improved detect ion rate.Figure 4-3 - Eye template weights used to give higher priority to those pixels that best represent the eyes.4.2 The Direct Correlation ApproachWe begi n our inv estigatio n into face recog niti on with perhaps the simplest approach,k nown as the direct correlation method (also referred to as template matching by Brunelli and Poggio [29 ]) inv olvi ng the direct comparis on of pixel inten sity values take n from facial images. We use the term ‘ Direct Correlation ' to encompass all techniques in which face images are compareddirectly, without any form of image space an alysis, weight ing schemes or feature extracti on, regardless of the dsta nee metric used. Therefore, we do not infer that Pears on ' s correlat applied as the similarity fun cti on (although such an approach would obviously come un der our definition of direct correlation). We typically use the Euclidean distance as our metric in these inv estigati ons (in versely related to Pears on ' s correlati on and can be con sidered as a scale tran slati on sen sitive form of image correlati on), as this persists with the con trast made betwee n image space and subspace approaches in later sect ions.Firstly, all facial images must be alig ned such that the eye cen tres are located at two specified pixel coord in ates and the image cropped to remove any backgro und in formati on. These images are stored as greyscale bitmaps of 65 by 82 pixels and prior to recog niti on con verted into a vector of 5330 eleme nts (each eleme nt containing the corresp onding pixel inten sity value). Each corresp onding vector can be thought of as describ ing a point with in a 5330 dime nsional image space. This simple prin ciple can easily be exte nded to much larger images: a 256 by 256 pixel image occupies a si ngle point in 65,536-dime nsional image space and again, similar images occupy close points within that space. Likewise, similar faces are located close together within the image space, while dissimilar faces are spaced far apart. Calculati ng the Euclidea n dista need, betwee n two facial image vectors (ofte n referred to as the query image q, and gallery imageg), we get an indication of similarity. A threshold is then applied to make the final verification decision.d q g (d threshold ? accept) d threshold ? reject ) . Equ. 4-14.2.1 Verification TestsThe primary concern in any face recognition system is its ability to correctly verify aclaimed identity or determine a person's most likely identity from a set of potential matches in a database. In order to assess a given system ' s ability to perform these tasks, a variety of evaluati on methodologies have arise n. Some of these an alysis methods simulate a specific mode of operatio n (i.e. secure site access or surveilla nee), while others provide a more mathematical description of data distribution in some classificatio n space. In additi on, the results gen erated from each an alysis method may be prese nted in a variety of formats. Throughout the experime ntatio ns in this thesis, weprimarily use the verification test as our method of analysis and comparison, although we also use Fisher Lin ear Discrim inant to an alyse in dividual subspace comp onents in secti on 7 and the iden tificati on test for the final evaluatio ns described in sect ion 8. The verificati on test measures a system ' s ability to correctly accept or reject the proposed ide ntity of an in dividual. At a fun cti on al level, this reduces to two images being prese nted for comparis on, for which the system must return either an accepta nee (the two images are of the same pers on) or rejectio n (the two images are of differe nt people). The test is desig ned to simulate the applicati on area of secure site access. In this scenario, a subject will present some form of identification at a point of en try, perhaps as a swipe card, proximity chip or PIN nu mber. This nu mber is the n used to retrieve a stored image from a database of known subjects (ofte n referred to as the target or gallery image) and compared with a live image captured at the point of entry (the query image). Access is the n gran ted depe nding on the accepta nce/rejecti on decisi on.The results of the test are calculated accord ing to how many times the accept/reject decisi on is made correctly. In order to execute this test we must first define our test set of face images. Although the nu mber of images in the test set does not affect the results produced (as the error rates are specified as percentages of image comparisons), it is important to ensure that the test set is sufficie ntly large such that statistical ano malies become in sig ni fica nt (for example, a couple of badly aligned images matching well). Also, the type of images (high variation in lighting, partial occlusions etc.) will significantly alter the results of the test. Therefore, in order to compare multiple face recog niti on systems, they must be applied to the same test set.However, it should also be no ted that if the results are to be represe ntative of system performance in a real world situation, then the test data should be captured under precisely the same circumsta nces as in the applicati on en vir onmen t. On the other han d, if the purpose of the experime ntati on is to evaluate and improve a method of face recog niti on, which may be applied to a range of applicati on en vir onmen ts, the n the test data should prese nt the range of difficulties that are to be overcome. This may mea n in cludi ng a greater perce ntage of ‘ difficult would be expected in the perceived operati ng con diti ons and hence higher error rates in the results produced. Below we provide the algorithm for execut ing the verificati on test. The algorithm is applied to a sin gle test set of face images, using a sin gle fun cti on call to the face recog niti on algorithm: CompareFaces(FaceA, FaceB). This call is used to compare two facial images, returni ng a dista nce score in dicat ing how dissimilar the two face images are: the lower the score the more similar the two face images. Ideally, images of the same face should produce low scores, while images of differe nt faces should produce high scores.Every image is compared with every other image, no image is compared with itself and no pair is compared more tha n once (we assume that the relati on ship is symmetrical). Once two images have been compared, producing a similarity score, the ground-truth is used to determine if the images are ofthe same person or different people. In practical tests this information is ofte n en capsulated as part of the image file name (by means of a unique pers on ide ntifier). Scores are the n stored in one of two lists: a list containing scores produced by compari ng images of differe nt people and a list containing scores produced by compari ng images of the same pers on. The final accepta nce/reject ion decisi on is made by applicati on of a threshold. Any in correct decision is recorded as either a false acceptance or false rejection. The false rejection rate (FRR) is calculated as the perce ntage of scores from the same people that were classified as rejectio ns. The false accepta nce rate (FAR) is calculated as the perce ntage of scores from differe nt people that were classified as accepta nces.For IndexA = 0 to length (TestSet)For IndexB = lndexA+1 to length (T estSet)Score = CompareFaces (T estSet[IndexA], TestSet[IndexB]) If IndexA and IndexB are the same person Append Score to AcceptScoresListElseAppend Score to RejectScoresListFor Threshold = Minimum Score to Maximum Score:FalseAcceptCount, FalseRejectCount = 0For each Score in RejectScoresListIf Score <= ThresholdIncrease FalseAcceptCountFor each Score in AcceptScoresListIf Score > ThresholdIncrease FalseRejectCountFalseAcceptRate = FalseAcceptCount / Length(AcceptScoresList) FalseRejectRate = FalseRejectCount / length(RejectScoresList) Add plot to error curve at (FalseRejectRate, FalseAcceptRate)These two error rates express the in adequacies of the system whe n operat ing at aspecific threshold value. Ideally, both these figures should be zero, but in reality reducing either the FAR or FRR (by alteri ng the threshold value) will in evitably resultin increasing the other. Therefore, in order to describe the full operating range of a particular system, we vary the threshold value through the en tire range of scores produced. The applicati on of each threshold value produces an additi onal FAR, FRR pair, which when plotted on a graph produces the error rate curve shown below.Figure 4-5 - Example Error Rate Curve produced by the verification test.The equal error rate (EER) can be see n as the point at which FAR is equal to FRR. This EER value is often used as a single figure representing the general recognition performa nee of a biometric system and allows for easy visual comparis on of multiple methods. However, it is important to note that the EER does not indicate the level of error that would be expected in a real world applicati on .It is un likely that any real system would use a threshold value such that the perce ntage of false accepta nces were equal to the perce ntage of false rejecti ons. Secure site access systems would typically set the threshold such that false accepta nces were sig nifica ntly lower tha n false rejecti ons: unwilling to tolerate intruders at the cost of inconvenient access denials.Surveilla nee systems on the other hand would require low false rejectio n rates to successfully ide ntify people in a less con trolled en vir onment. Therefore we should bear in mind that a system with a lower EER might not n ecessarily be the better performer towards the extremes of its operating capability.There is a strong conn ecti on betwee n the above graph and the receiver operat ing characteristic (ROC) curves, also used in such experime nts. Both graphs are simply two visualisati ons of the same results, in that the ROC format uses the True Accepta nee Rate(TAR), where TAR = 1.0 -FRR in place of the FRR, effectively flipping the graph vertically. Another visualisation of the verification test results is to display both the FRR and FAR as functions of the threshold value. This prese ntati on format provides a refere nee to determ ine the threshold value necessary to achieve a specific FRR and FAR. The EER can be seen as the point where the two curves in tersect.ThrasholdFigure 4-6 - Example error rate curve as a function of the score thresholdThe fluctuati on of these error curves due to no ise and other errors is depe ndant on the nu mber of face image comparis ons made to gen erate the data. A small dataset that on ly allows for a small nu mber of comparis ons will results in a jagged curve, in which large steps corresp ond to the in flue nce of a si ngle image on a high proporti on of thecomparis ons made. A typical dataset of 720 images (as used in sect ion 422) provides 258,840 verificatio n operati ons, hence a drop of 1% EER represe nts an additi onal 2588 correct decisions, whereas the quality of a single image could cause the EER tofluctuate by up to 0.28.4.2.2 ResultsAs a simple experiment to test the direct correlation method, we apply the technique described above to a test set of 720 images of 60 different people, taken from the AR Face Database [ 39 ]. Every image is compared with every other image in the test set to produce a like ness score, provid ing 258,840 verificati on operati ons from which to calculate false accepta nce rates and false rejecti on rates. The error curve produced is show n in Figure 4-7.Figure 4-7 - Error rate curve produced by the direct correlation method using no image preprocessing.We see that an EER of 25.1% is produced, meaning that at the EER thresholdapproximately one quarter of all verification operations carried out resulted in anin correct classificati on. There are a nu mber of well-k nown reas ons for this poor levelof accuracy. Tiny changes in lighting, expression or head orientation cause the location in image space to cha nge dramatically. Images in face space are moved far apart due to these image capture conditions, despite being of the same person ' s face. The distanee between images differe nt people becomes smaller tha n the area of face space covered by images of the same pers on and hence false accepta nces and false rejecti ons occur freque ntly. Other disadva ntages in clude the large amount of storage n ecessary for holdi ng many face images and the inten sive process ing required for each comparis on, making this method un suitable for applicati ons applied to a large database. In secti on 4.3 we explore the eige nface method, which attempts to address some of these issues.4二维人脸识别4.1功能定位在讨论比较两个人脸图像，我们现在就简要介绍的方法一些在人脸特征的初步调整过程。

人脸识别技术的中英文论文

①现代的人脸识别，特指通过分析、比较人脸视觉特征信息进行身份鉴别的计算机技术。

具体而言，就是通过视频采集设备获取识别对象的面部图像，再利用核心的算法对其脸部的五官位置、脸型和角度进行计算分析，进而和自身数据库里已有的范本进行比对，最后判断出用户的真实身份。

这是一项高端的计算机图像处理技术。

②在全球范围内，人脸识别系统的研究始于20 世纪60 年代。

人脸识别的优势在于其自然性和不被被测个体察觉的特点。

所谓自然性，是指该识别方式同人类（甚至其他生物）进行个体识别时所利用的生物特征相同。

人脸识别就是通过观察比较人脸来区分和确认身份的。

不被察觉的特点会使该识别方法不令人反感，并且因为不容易引起人的注意而不易被欺骗。

相对于指纹识别而言，人脸识别还具有非接触式（非侵犯式）的特点，因此更加友好、自然，更易被人们接受。

③随着科技的发展，人脸识别技术的应用已经不是什么新鲜事了。

《基于人脸识别的智能公交支付系统》英文文献

《基于人脸识别的智能公交支付系统》英文文献以下是一篇关于《基于人脸识别的智能公交支付系统》的英文文献的示例：Title: Intelligent Bus Payment System Based on Face RecognitionAbstract:With the rapid development of intelligent transportation systems, there is a growing demand for efficient and convenient payment methods in public transportation. In this paper, we propose an intelligent bus payment system based on face recognition technology. The system utilizes advanced computer vision algorithms to accurately identify passengers' faces and link them to their payment accounts. This eliminates the need for traditional ticketing systems or smart cards, providing a more seamless and user-friendly experience for commuters.The proposed system consists of three main components: face detection, face recognition, and payment integration. Firstly, a robust face detection algorithm is employed to locate and extract facial features from the captured images or video streams. Then, a state-of-the-art face recognition model is utilized to match the detected faces with registered users in the database. Finally, the payment integration module securely links the recognized faces with the associated payment accounts, allowing for real-time transactions during bus boarding.To evaluate the performance of the system, we conducted experiments using a large dataset of passenger images collected from different scenarios. The results demonstrate the effectiveness and accuracy of the proposed face recognition algorithm, achieving a high recognition rate even under varying lighting conditions and occlusion. Additionally, the system showed promising results in terms of transaction speed and reliability, making it a viable solution for intelligent bus payment systems.In conclusion, the proposed intelligent bus payment system based on face recognition technology offers a secure and convenient alternative to traditional ticketing systems. It has the potential to revolutionize public transportation by simplifying the payment process and improving overall efficiency. Further research and development are warranted to address potential challenges and ensure widespread adoption of this innovative solution.Keywords: Intelligent transportation systems, Face recognition, Public transportation, Payment integration, Computer vision.请注意，以上是一个示例的文献摘要，实际的英文文献可能具有不同的结构和内容。

中外文文献-基于pca的人脸识别

外文资料原文An Improved Hybrid Face Recognition Based on PCA andSubpattern TechniqueA.R Kulkarni, D.S BormaneAbstract: In this paper a new technique for face recognition Based on PCA is implement ed .Subpattern PCA(SpPCA) Is actually an improvement over PCA. It was found to give Better results so in this paper Integration of Different SpPCA methods with PCA was do ne and found to get Improvement in recognition Accuracy.Keyword s: Principle Component Analysis (PCA, Subpattern PCA(SpPCA), SpPCA I, SpP CAIII. INTRODUCTIONHumans have been using physical characteristics such as face, voice, gait, etc. to reco gnize each other for thousands of years. With new advances in technology, biometrics has become an emerging technology for recognizing individuals using their biological traits. Now, biometrics is becoming part of day to day life, where in a person is recognized by his/her personal biological characteristics. Examples of different Biometric systems include Fingerprint recognition, Face recognition, Iris recognition, Retina recognition, Hand geometr y, V oice recognition, Signature recognition, among others. Face recognition, in particular ha s received a considerable attention in recent years both from the industry and the research community.A) Facial Expression RecognitionRecognition of facial expression is important in human computer interaction, human robot interaction, digital entertainments, games, smart user interface for cellular phones and game s. Recognition of facial expression by using computer is a topic that has become under c onsideration not more than a decade. Facial expression in human is a reaction to analeptic s. For example reaction to a funny movie is laughter, laughing changes the figure of the face and state of the face muscles. By tracing these states changing and comparing them with the neutral face, facial expression can be recognized. Primary facial expressions whic h are anger, disgust, fear, happiness, sadness and surprise. Figure 1 illustrates these states of expressions. Implementing real time facial expression recognition is difficult and does n ot have impressive results because of person, camera, and illumination variations complicat e the distribution of the facial expressions. In this paper facial expressions are recognized by using still images.Manuscript received May, 2013Er .A. R. Kulkarni, received her Bachelor of Engg. Degree from W.C.E Sangli, Shivaji University, Maharashtra, India.Prof .Dr D.S Bormane , is the Director for JSPM’s Rajarshi Shahu College Of Engg, p une India.Fig.1 illustrates 6 states of facial ExpressionsHumans have been using physical characteristics such as face, voice, gait, etc. to recognize each other for thousands of years. With new advances in technology, biometrics has become an emerging technology for recognizing individuals using their biological traits. Now, biometrics is becoming part of day to day life, where in a person is recognized by his/her personal biological characteristics. Examples of different Biometric systems include Fingerprint recognition, Face recognition, Iris recognition, Retina recognition, Hand geometry, V oice recognition, Signature recognition, among others. Face recognition, in particular has received a considerable attention in recent years both from the industry and the research community. PCA, SpPCA are the feature extraction methods which have been used in this report in order to recognize the facial expressions. Each of the mentioned method shows different performance in terms of recognizing the expressions. The objective of our project is to create a matlab code that can be used to identify people using their face images.An Improved Hybrid Face Recognition Based on PCA and Subpattern TechniqueThis papert gives a brief background about biometrics. A particular attention is given to face recognition. Face recognition refers to an automated or semi-automated process of matching facial images. Many techniques are available to apply face recognition of which is Principle Component Analysis (PCA). PCA is a way of identifying patterns in data and expressing the data in such a way to highlight their similarities and differences. Before applying this method to face recognition, a brief introduction is given for PCA. SpPCAI & SpPCAII has also been applied. The Matlab code for a Hybrid Algorithm has been designed which consists integration of SpPCAI with SpPCAII. Thetraditional PCA [1] is a very effective approach of extracting features and has successfully been applied in pattern recognition such as face classification [2]. It operates directly on whole patterns represented as (feature) vectors to extract so-needed global features for subsequent classification by a set of previously found global projectors from a given training pattern set, whose aim is to maximally preserve original pattern information after extracting features, i.e., reducing dimensionality. In this paper, we develop another PCA operating directly on sub patterns rather than on whole pattern These sub patterns are formed via a partition for an original whole pattern and utilized to compose multiple training Subpattern sets for the original training pattern set. In this way, SpPCA can independently be performed on individual training subpattern sets and finds corresponding local projection sub-V ectors, and then uses them to extract local sub-features from any given pattern. Afterwards, these extracted sub-features from individual subpatterns are synthesized into a global feature of the original whole pattern for subsequent classification.II. PRINCIPAL COMPONENT ANALYSIS (PCA)The purpose of PCA is to reduce the dimensionality of data sets without losing significant information PCA is reducing the dimensionality of data set by performing covariance analysis between multidimensional data sets [31, 32]. Because PCA is classical technique that can do something in linear domain, applications that have linear models are suitable, for image processing. The main idea of using PCA for face recognition is to express the large 1-D vector of pixels constructed from 2-D facial image into the compact principal components of the feature space. This can be called eigenspace projection. Eigenspace is calculated by identifying the eigenvectors of the covariance matrix derived from a set of facial images (vectors)Fig.2 Original cropped image and image with 4 non-overlapped subpatternsII. PROPOSED SPPCAFig.3 Flowchart for Subpattern techniqueSpPCA includes two steps. In the first step, an original whole pattern denoted by a vector is partitioned into a set of equally-sized subpatterns in non-overlapping ways and then all those subpatterns sharing the same original feature components are respectively collected from the training set to compose Corresponding training subpattern setsas shown in “Fig1”. Secondly, PCA is performed on each of such subpattern sets. More specifically, we are given a set of training patterns X={X1 ,X2 , …XN, } with each column vector Xi for (i=1, 2, …, N) having m dimensions. Now according to the first step, an original whole pattern is firstpartitioned into K d- dimensional subpatterns in a non overlapping way and reshaped into a d-by-K matrix Xi=(Xi1,Xi2……Xik) , with Xij being the jth subpattern of Xi and i=1,2,…, N and j=1,2,…,K. And then according to the second step, we construct PCA for the jth subpattern set SPj= Xij,i=1,2….,N ) to seek its projection vectors Φj =(¢j1,¢j2,..¢jl) Here it is easy toprove that all total subscatter matrices are positive semi-definite and their scales are all dxd. And then find independently each set of projection sub-vectors by means of the following eigen value-eigenvector system under the constraints. After obtaining all individual projection sub-vectors from the partitioned subpattern sets, we can extract corresponding sub-features from any subpattern of a given whole pattern Then synthesize them into a global feature . Now on the basis of the synthesized global features, we can use the nearest neighbor (NN) rule [3] to perform pattern classification.Fig4 . Block Diagram for Hybrid ImplementationA) Algorithm for proposed Hybrid SchemeStep 1: Create database from input imageStep 2: Read Train and Test imageStep 3: Perform SpPCA I and SpPCA IIStep 4: Calculate The Recognition RatesStep5.Calculatetheoveralldistance Computation and classification.Step 6. Calculate the Recognition rate for Hybrid methodIII. EXPERIMENTAL RESULTSIn this paper, experiments are based on ORL face database, which can be used freely for academic research [7]. ORL face database contains 40 distinct persons, each person having ten different face images. There are 400 face images in total, with 256 gray degrees and the resolution of 92112×. These face images are attained in different situations, such as different time, different angles, different expression (closed eyes/open eyes, smile/surprise/angry/happy etc.) and different face details (glasses/no glasses, beard/no beard, different hair style etc.). Some images are shown inFig.2.A) Graphical Result Of Algorithms ImplementedFig7. PCAFig 8 . SpPCA IFig.9 SpPCAIIFig10.hybridFig11.Overall Recognition accuracyB) T able.1 Recognition Accuracy ComparisionC) Algorithm Comparision ChartFig.12 Recognition RateIV. CONCLUSIONA Hybrid Approach for face Recognition using Subpattern Technique is implemented. In this paper facial expression recognition using PCA, SpPCA approaches were done and compared...The results of experiments demonstrate SpPCA overcome PCA.. Therefore integration of SpPCA with PCA was done and found recognition accuracy to be improved. We can therefore say that our novel hybrid approach is robust and competitive.V. FUTURE SCOPEFace recognition has recently become a very active and interesting research area. Vigorous research has been conducted in this area for the past four decades and huge progress w ith encouraging results has been obtained. The goal of this paper is to provide a survey of recentholistic and feature based approaches that complement previous surveys. Current face recognition systems have already reached a certain level of maturity when operating under constrained conditions. However, we are still far from achieving the ideal and adequate results in all the various situations. Still more advances need to be done in the technology regarding the sensitivity of the face images to environmental conditions like illumination, occlusion, time-delays, pose orientations, facial expressions. Furthermore, research work on 3 D face recognition and face recognition in videos is also pacing parallel. However, the error rates of current face recognition systems are still too high for many of the applications. So, the researchers still need to go far to get accurate face recognitions.REFERENCES[1] T. Y oung, K-S Fu, Handbook of pattern recognition and image processing, Academic Press, 1986.[2] M. Turk, A. Pentland, Eigenfaces for recognition, Journal Cognitive Neuroscience, 3(1) (1991)71-86.[3] G. Loizou, S.J. Maybank, The nearest neighbor and the Bayes error rates, IEEE Trans. Patt. Anal. & Mach. Intell., vol.9 (1987)254-262,.[4] Seema Asht, Rajeshwar Dass, Dharmendar, “Pattern Recognition Techniques”, International Journal of Science, Engineering and Computer Technology, vol. 2, pp. 87-88, March 2012. [4] M. Kirby, L. Sirovich, “Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, No. 1, pp. 103-108, January 1990.[5] M. Turk and A. Pentland. “Face recognition using eigenfaces”. In Proceedings of the IEEE Conference on Computer V ision and Pattern Recognition, 1991[6] Face Recognition : National Science and Technology Council (NSTC) , Committee on Technology, Committee on Homeland and National Security, Subcommittee on biometrics.[7] N. Sun, H. Wang, Z. Ji, C. Zou, and L. Zhao, "An efficient algorithm for Kernel two-dimensional principal component analysis," Neural Computing & Applications, vol.17, pp.59-64, 2008.[8] Q. Y ang aand X. Q. Ding, "Symmetrical Principal Component Analysis and Its Application in Face Recognition," Chinese Journal of Computers, vol.26, pp.1146–1151, 2003.[9] J. Y ang and D. Zhang, "Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol.28, pp.131- 137, 2004.[10] K. R. Tan and S. C. Chen, "Adaptively weighted subpattern PCA for face recognition," Neurocomputing, vol.64, pp.505-511, 2005.外文资料译文一种基于PCA和子模式改进的混合人脸识别技术A.R Kulkarni, D.S Bormane摘要: 本文基于PCA人脸识别新技术实现的。

人脸识别技术外文翻译文献编辑

文献信息文献标题：Face Recognition Techniques: A Survey（人脸识别技术综述）文献作者：V.Vijayakumari文献出处：《World Journal of Computer Application and Technology》, 2013,1(2):41-50字数统计：英文3186单词，17705字符；中文5317汉字外文文献Face Recognition Techniques: A Survey Abstract Face is the index of mind. It is a complex multidimensional structure and needs a good computing technique for recognition. While using automatic system for face recognition, computers are easily confused by changes in illumination, variation in poses and change in angles of faces. A numerous techniques are being used for security and authentication purposes which includes areas in detective agencies and military purpose. These surveys give the existing methods in automatic face recognition and formulate the way to still increase the performance.Keywords: Face Recognition, Illumination, Authentication, Security1.IntroductionDeveloped in the 1960s, the first semi-automated system for face recognition required the administrator to locate features ( such as eyes, ears, nose, and mouth) on the photographs before it calculated distances and ratios to a common reference point, which were then compared to reference data. In the 1970s, Goldstein, Armon, and Lesk used 21 specific subjective markers such as hair color and lip thickness to automate the recognition. The problem with both of these early solutions was that the measurements and locations were manually computed. The face recognition problem can be divided into two main stages: face verification (or authentication), and face identification (or recognition).The detection stage is the first stage; it includesidentifying and locating a face in an image. The recognition stage is the second stage; it includes feature extraction, where important information for the discrimination is saved and the matching where the recognition result is given aid of a face database.2.Methods2.1.Geometric Feature Based MethodsThe geometric feature based approaches are the earliest approaches to face recognition and detection. In these systems, the significant facial features are detected and the distances among them as well as other geometric characteristic are combined in a feature vector that is used to represent the face. To recognize a face, first the feature vector of the test image and of the image in the database is obtained. Second, a similarity measure between these vectors, most often a minimum distance criterion, is used to determine the identity of the face. As pointed out by Brunelli and Poggio, the template based approaches will outperform the early geometric feature based approaches.2.2.Template Based MethodsThe template based approaches represent the most popular technique used to recognize and detect faces. Unlike the geometric feature based approaches, the template based approaches use a feature vector that represent the entire face template rather than the most significant facial features.2.3.Correlation Based MethodsCorrelation based methods for face detection are based on the computation of the normalized cross correlation coefficient Cn. The first step in these methods is to determine the location of the significant facial features such as eyes, nose or mouth. The importance of robust facial feature detection for both detection and recognition has resulted in the development of a variety of different facial feature detection algorithms. The facial feature detection method proposed by Brunelli and Poggio uses a set of templates to detect the position of the eyes in an image, by looking for the maximum absolute values of the normalized correlation coefficient of these templates at each point in test image. To cope with scale variations, a set of templates atdifferent scales was used.The problems associated with the scale variations can be significantly reduced by using hierarchical correlation. For face recognition, the templates corresponding to the significant facial feature of the test images are compared in turn with the corresponding templates of all of the images in the database, returning a vector of matching scores computed through normalized cross correlation. The similarity scores of different features are integrated to obtain a global score that is used for recognition. Other similar method that use correlation or higher order statistics revealed the accuracy of these methods but also their complexity.Beymer extended the correlation based on the approach to a view based approach for recognizing faces under varying orientation, including rotations with respect to the axis perpendicular to the image plane(rotations in image depth). To handle rotations out of the image plane, templates from different views were used. After the pose is determined ,the task of recognition is reduced to the classical correlation method in which the facial feature templates are matched to the corresponding templates of the appropriate view based models using the cross correlation coefficient. However this approach is highly computational expensive, and it is sensitive to lighting conditions.2.4.Matching Pursuit Based MethodsPhilips introduced a template based face detection and recognition system that uses a matching pursuit filter to obtain the face vector. The matching pursuit algorithm applied to an image iteratively selects from a dictionary of basis functions the best decomposition of the image by minimizing the residue of the image in all iterations. The algorithm describes by Philips constructs the best decomposition of a set of images by iteratively optimizing a cost function, which is determined from the residues of the individual images. The dictionary of basis functions used by the author consists of two dimensional wavelets, which gives a better image representation than the PCA (Principal Component Analysis) and LDA(Linear Discriminant Analysis) based techniques where the images were stored as vectors. For recognition the cost function is a measure of distances between faces and is maximized at each iteration. For detection the goal is to find a filter that clusters together in similar templates (themean for example), and minimized in each iteration. The feature represents the average value of the projection of the templates on the selected basis.2.5.Singular Value Decomposition Based MethodsThe face recognition method in this section use the general result stated by the singular value decomposition theorem. Z.Hong revealed the importance of using Singular Value Decomposition Method (SVD) for human face recognition by providing several important properties of the singular values (SV) vector which include: the stability of the SV vector to small perturbations caused by stochastic variation in the intensity image, the proportional variation of the SV vector with the pixel intensities, the variances of the SV feature vector to rotation, translation and mirror transformation. The above properties of the SV vector provide the theoretical basis for using singular values as image features. In addition, it has been shown that compressing the original SV vector into the low dimensional space by means of various mathematical transforms leads to the higher recognition performance. Among the various dimensionality reducing transformations, the Linear Discriminant Transform is the most popular one.2.6.The Dynamic Link Matching MethodsThe above template based matching methods use an Euclidean distance to identify a face in a gallery or to detect a face from a background. A more flexible distance measure that accounts for common facial transformations is the dynamic link introduced by Lades et al. In this approach , a rectangular grid is centered all faces in the gallery. The feature vector is calculated based on Gabor type wavelets, computed at all points of the grid. A new face is identified if the cost function, which is a weighted sum of two terms, is minimized. The first term in the cost function is small when the distance between feature vectors is small and the second term is small when the relative distance between the grid points in the test and the gallery image is preserved. It is the second term of this cost function that gives the “elasticity” of this matching measure. While the grid of the image remains rectangular, the grid that is “best fit” over the test image is stretched. Under certain constraints, until the minimum of the cost function is achieved. The minimum value of the cost function isused further to identify the unknown face.2.7.Illumination Invariant Processing MethodsThe problem of determining functions of an image of an object that are insensitive to illumination changes are considered. An object with Lambertian reflection has no discriminative functions that are invariant to illumination. This result leads the author to adopt a probabilistic approach in which they analytically determine a probability distribution for the image gradient as a function of the surfaces geometry and reflectance. Their distribution reveals that the direction of the image gradient is insensitive to changes in illumination direction. Verify this empirically by constructing a distribution for the image gradient from more than twenty million samples of gradients in a database of thousand two hundred and eighty images of twenty inanimate objects taken under varying lighting conditions. Using this distribution, they develop an illumination insensitive measure of image comparison and test it on the problem of face recognition. In another method, they consider only the set of images of an object under variable illumination, including multiple, extended light sources, shadows, and color. They prove that the set of n-pixel monochrome images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IR and that the dimension of this illumination cone equals the number of distinct surface normal. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRn. These results immediately suggest certain approaches to object recognition. Throughout, they present results demonstrating the illumination cone representation.2.8.Support Vector Machine ApproachFace recognition is a K class problem, where K is the number of known individuals; and support vector machines (SVMs) are a binary classification method. By reformulating the face recognition problem and reinterpreting the output of the SVM classifier, they developed a SVM-based face recognition algorithm. The facerecognition problem is formulated as a problem in difference space, which models dissimilarities between two facial images. In difference space we formulate face recognition as a two class problem. The classes are: dissimilarities between faces of the same person, and dissimilarities between faces of different people. By modifying the interpretation of the decision surface generated by SVM, we generated a similarity metric between faces that are learned from examples of differences between faces. The SVM-based algorithm is compared with a principal component analysis (PCA) based algorithm on a difficult set of images from the FERET database. Performance was measured for both verification and identification scenarios. The identification performance for SVM is 77-78% versus 54% for PCA. For verification, the equal error rate is 7% for SVM and 13% for PCA.2.9.Karhunen- Loeve Expansion Based Methods2.9.1.Eigen Face ApproachIn this approach, face recognition problem is treated as an intrinsically two dimensional recognition problem. The system works by projecting face images which represents the significant variations among known faces. This significant feature is characterized as the Eigen faces. They are actually the eigenvectors. Their goal is to develop a computational model of face recognition that is fact, reasonably simple and accurate in constrained environment. Eigen face approach is motivated by the information theory.2.9.2.Recognition Using Eigen FeaturesWhile the classical eigenface method uses the KLT (Karhunen- Loeve Transform) coefficients of the template corresponding to the whole face image, the author Pentland et.al. introduce a face detection and recognition system that uses the KLT coefficients of the templates corresponding to the significant facial features like eyes, nose and mouth. For each of the facial features, a feature space is built by selecting the most significant “eigenfeatures”, which are the eigenvectors corresponding to the largest eigen values of the features correlation matrix. The significant facial features were detected using the distance from the feature space and selecting the closest match. The scores of similarity between the templates of the test image and thetemplates of the images in the training set were integrated in a cumulative score that measures the distance between the test image and the training images. The method was extended to the detection of features under different viewing geometries by using either a view-based Eigen space or a parametric eigenspace.2.10.Feature Based Methods2.10.1.Kernel Direct Discriminant Analysis AlgorithmThe kernel machine-based Discriminant analysis method deals with the nonlinearity of the face patterns’ distribution. This method also effectively solves the so-called “small sample size” (SSS) problem, which exists in most Face Recognition tasks. The new algorithm has been tested, in terms of classification error rate performance, on the multiview UMIST face database. Results indicate that the proposed methodology is able to achieve excellent performance with only a very small set of features being used, and its error rate is approximately 34% and 48% of those of two other commonly used kernel FR approaches, the kernel-PCA (KPCA) and the Generalized Discriminant Analysis (GDA), respectively.2.10.2.Features Extracted from Walshlet PyramidA novel Walshlet Pyramid based face recognition technique used the image feature set extracted from Walshlets applied on the image at various levels of decomposition. Here the image features are extracted by applying Walshlet Pyramid on gray plane (average of red, green and blue. The proposed technique is tested on two image databases having 100 images each. The results show that Walshlet level-4 outperforms other Walshlets and Walsh Transform, because the higher level Walshlets are giving very coarse color-texture features while the lower level Walshlets are representing very fine color-texture features which are less useful to differentiate the images in face recognition.2.10.3.Hybrid Color and Frequency Features ApproachThis correspondence presents a novel hybrid Color and Frequency Features (CFF) method for face recognition. The CFF method, which applies an Enhanced Fisher Model(EFM), extracts the complementary frequency features in a new hybrid color space for improving face recognition performance. The new color space, the RIQcolor space, which combines the component image R of the RGB color space and the chromatic components I and Q of the YIQ color space, displays prominent capability for improving face recognition performance due to the complementary characteristics of its component images. The EFM then extracts the complementary features from the real part, the imaginary part, and the magnitude of the R image in the frequency domain. The complementary features are then fused by means of concatenation at the feature level to derive similarity scores for classification. The complementary feature extraction and feature level fusion procedure applies to the I and Q component images as well. Experiments on the Face Recognition Grand Challenge (FRGC) show that i) the hybrid color space improves face recognition performance significantly, and ii) the complementary color and frequency features further improve face recognition performance.2.10.4.Multilevel Block Truncation Coding ApproachIn Multilevel Block Truncation coding for face recognition uses all four levels of Multilevel Block Truncation Coding for feature vector extraction resulting into four variations of proposed face recognition technique. The experimentation has been conducted on two different face databases. The first one is Face Database which has 1000 face images and the second one is “Our Own Database” which has 1600 face images. To measure the performance of the algorithm the False Acceptance Rate (FAR) and Genuine Acceptance Rate (GAR) parameters have been used. The experimental results have shown that the outcome of BTC (Block truncation Coding) Level 4 is better as compared to the other BTC levels in terms of accuracy, at the cost of increased feature vector size.2.11.Neural Network Based AlgorithmsTemplates have been also used as input to Neural Network (NN) based systems. Lawrence et.al proposed a hybrid neural network approach that combines local image sampling, A self organizing map (SOM) and a convolutional neural network. The SOP provides a set of features that represents a more compact and robust representation of the image samples. These features are then fed into the convolutional neural network. This architecture provides partial invariance to translation, rotation, scale and facedeformation. Along with this the author introduced an efficient probabilistic decision based neural network (PDBNN) for face detection and recognition. The feature vector used consists of intensity and edge values obtained from the facial region of the down sampled image in the training set. The facial region contains the eyes and nose, but excludes the hair and mouth. Two PDBNN were trained with these feature vectors and used one for the face detection and other for the face recognition.2.12.Model Based Methods2.12.1.Hidden Markov Model Based ApproachIn this approach, the author utilizes the face that the most significant facial features of a frontal face which includes hair, forehead, eyes, nose and mouth which occur in a natural order from top to bottom even if the image undergo small variation/rotation in the image plane perpendicular to the image plane. One dimensional HMM (Hidden Markov Model) is used for modeling the image, where the observation vectors are obtained from DCT or KLT coefficients. They given c face images for each subject of the training set, the goal of the training set is to optimize the parameters of the Hidden Markov Model to best describe the observations in the sense of maximizing the probability of the observations given in the model. Recognition is carried out by matching the best test image against each of the trained models. To do this, the image is converted to an observation sequence and then model likelihoods are computed for each face model. The model with the highest likelihood reveals the identity of the unknown face.2.12.2.The Volumetric Frequency Representation of Face ModelA face model that incorporates both the three dimensional (3D) face structure and its two-dimensional representation are explained (face images). This model which represents a volumetric (3D) frequency representation (VFR) of the face , is constructed using range image of a human head. Making use of an extension of the projection Slice Theorem, the Fourier transform of any face image corresponds to a slice in the face VFR. For both pose estimation and face recognition a face image is indexed in the 3D VFR based on the correlation matching in a four dimensional Fourier space, parameterized over the elevation, azimuth, rotation in the image planeand the scale of faces.3.ConclusionThis paper discusses the different approaches which have been employed in automatic face recognition. In the geometrical based methods, the geometrical features are selected and the significant facial features are detected. The correlation based approach needs face template rather than the significant facial features. Singular value vectors and the properties of the SV vector provide the theoretical basis for using singular values as image features. The Karhunen-Loeve expansion works by projecting the face images which represents the significant variations among the known faces. Eigen values and Eigen vectors are involved in extracting the features in KLT. Neural network based approaches are more efficient when it contains no more than a few hundred weights. The Hidden Markov model optimizes the parameters to best describe the observations in the sense of maximizing the probability of observations given in the model .Some methods use the features for classification and few methods uses the distance measure from the nodal points. The drawbacks of the methods are also discussed based on the performance of the algorithms used in the approaches. Hence this will give some idea about the existing methods for automatic face recognition.中文译文人脸识别技术综述摘要人脸是心灵的指标。

人脸识别便捷性的英语作文

人脸识别便捷性的英语作文Facial recognition technology has become increasingly prevalent in our daily lives, offering a convenient and efficient way to authenticate our identity. This innovative technology has transformed the way we interact with various systems and devices, making our lives more seamless and secure. In this essay, we will explore the advantages and potential drawbacks of facial recognition technology, and discuss its impact on our society.One of the primary benefits of facial recognition is its convenience. Gone are the days when we had to remember countless passwords or carry around physical identification cards. With facial recognition, we can simply look at our devices, and they will instantly recognize us, granting us access to our accounts, devices, and even secure facilities. This streamlined process saves us time and effort, allowing us to focus on more important tasks.Moreover, facial recognition technology enhances security by providing a robust and reliable method of identification. Traditional forms of identification, such as passwords and ID cards, can be easily lost, stolen, or compromised. Facial recognition, on the other hand, relies on unique biometric data that is virtually impossible toreplicate, making it a more secure option for protecting sensitive information and assets.In the realm of law enforcement, facial recognition has proven to be a valuable tool in identifying and apprehending criminals. By cross-referencing facial images with extensive databases, law enforcement agencies can quickly and accurately identify suspects, aiding in the investigation and prosecution of crimes. This technology has the potential to significantly improve public safety and deter criminal activity.Another area where facial recognition has made a significant impact is in the field of healthcare. Healthcare providers can use this technology to quickly and accurately identify patients, ensuring that they receive the appropriate treatment and medication. This can be particularly beneficial in emergency situations, where every second counts. Additionally, facial recognition can be used to monitor patient well-being, alerting healthcare professionals to any changes or concerns.However, the widespread use of facial recognition technology has also raised concerns about privacy and civil liberties. There are valid concerns that this technology could be misused or abused, leading to the surveillance of individuals without their consent. There are also worries that facial recognition databases could be hacked oraccessed by unauthorized parties, putting sensitive personal information at risk.To address these concerns, policymakers and technology companies must work together to develop robust regulations and security measures to protect the privacy and rights of individuals. This may include implementing strict data-sharing protocols, ensuring transparency in the use of facial recognition technology, and providing individuals with the ability to opt-out or control how their facial data is used.Furthermore, the accuracy and reliability of facial recognition technology must be carefully evaluated and improved. Certain studies have shown that facial recognition algorithms can exhibit bias and inaccuracies, particularly when it comes to identifying individuals with diverse racial and ethnic backgrounds. It is crucial that these issues are addressed to ensure that the technology is fair and equitable for all users.In conclusion, facial recognition technology has revolutionized the way we interact with the world around us. Its convenience, security, and potential applications in various industries make it a valuable tool. However, we must also be mindful of the potential risks and work to address them through responsible development and implementation of this technology. By striking a balance between thebenefits and the concerns, we can harness the power of facial recognition to improve our lives while safeguarding our fundamental rights and freedoms.。

英文翻译

成都信息工程学院毕业设计英文翻译介绍了人脸检测和人脸识别系别电子工程学院姓名王雄专业电子信息工程班级信号处理2班学号2010021176Introduction to Face Detection and Face RecognitionLast updated on 4th Feb, 2012 by Shervin Emami. Posted originally on 2nd June, 2010."Face Recognition" is a very active area in the Computer Vision and Biometrics fields, as it has been studied vigorously for 25 years and is finally producing applications in security, robotics, human-computer-interfaces, digital cameras, games and entertainment."Face Recognition" generally involves two stages:Face Detection, where a photo is searched to find any face (shown here as a green rectangle), then image processing cleans up the facial image for easier recognition. Face Recognition, where that detected and processed face is compared to a database of known faces, to decide who that person is (shown here as red text).Since 2002, Face Detection can be performed fairly reliably such as with OpenCV's Face Detector, working in roughly 90-95% of clear photos of a person looking forward at the camera. It is usually harder to detect a person's face when they are viewed from the side or at an angle, and sometimes this requires 3D Head Pose Estimation. It can also be very difficult to detect a person's face if the photo is not very bright, or if part of the face is brighter than another or has shadows or is blurry or wearing glasses, etc. However, Face Recognition is much less reliable than Face Detection, generally 30-70% accurate. Face Recognition has been a strong field of research since the 1990s, but is still far from reliable, and more techniques are being invented each year such as the ones listed at the bottom of this page (Alternatives to Eigenfaces such as 3D face recognition or recognition from video).I will show you how to use Eigenfaces (also called "Principal Component Analysis" or PCA), a simple and popular method of 2D Face Recognition from a photo, as opposed to other common methods such as Neural Networks orFisher Faces.To learn the theory of how Eigenface works, you should read Face Recognition With Eigenface from Servo Magazine (April 2007), and perhaps the mathematical algorithm. First I will explain how to implement Eigenfaces for offline training from the command-line, based on the Servo Magazine tutorial and source-code (May 2007). Once I have explained to you how offline training and offline face recognition works from the command-line, I will explain how this can be extended to online training directly from a webcam in realtime :-)How to detect a face using OpenCV's Face Detector:As mentioned above, the first stage in Face Recognition is Face Detection. The OpenCV library makes it fairly easy to detect a frontal face in an image using its Haar Cascade Face Detector (also known as the Viola-Jones method).The function "cvHaarDetectObjects" in OpenCV performs the actual face detection, but the function is a bit tedious to use directly, so it is easiest to use this wrapper function: // Perform face detection on the input image, using the given Haar Cascade. // Returns a rectangle for the detected region in the given image.CvRect detectFaceInImage(IplImage *inputImg, CvHaarClassifierCascade* cascade) {// Smallest face size.CvSize minFeatureSize = cvSize(20, 20);// Only search for 1 face.int flags = CV_HAAR_FIND_BIGGEST_OBJECT | CV_HAAR_DO_ROUGH_SEARCH;// How detailed should the search be.float search_scale_factor = 1.1f;IplImage *detectImg;IplImage *greyImg = 0;CvMemStorage* storage;CvRect rc;double t;CvSeq* rects;CvSize size;int i, ms, nFaces;storage = cvCreateMemStorage(0);cvClearMemStorage( storage );// If the image is color, use a greyscale copy of the image.detectImg = (IplImage*)inputImg;if (inputImg->nChannels > 1) {size = cvSize(inputImg->width, inputImg->height);greyImg = cvCreateImage(size, IPL_DEPTH_8U, 1 );cvCvtColor( inputImg, greyImg, CV_BGR2GRAY );detectImg = greyImg; // Use the greyscale image.}// Detect all the faces in the greyscale image.t = (double)cvGetTickCount();rects = cvHaarDetectObjects( detectImg, cascade, storage,search_scale_factor, 3, flags, minFeatureSize);t = (double)cvGetTickCount() - t;ms = cvRound( t / ((double)cvGetTickFrequency() * 1000.0) );nFaces = rects->total;printf("Face Detection took %d ms and found %d objects\n", ms, nFaces);// Get the first detected face (the biggest).if (nFaces > 0)rc = *(CvRect*)cvGetSeqElem( rects, 0 );elserc = cvRect(-1,-1,-1,-1); // Couldn't find the face.if (greyImg)cvReleaseImage( &greyImg );cvReleaseMemStorage( &storage );//cvReleaseHaarClassifierCascade( &cascade );return rc; // Return the biggest face found, or (-1,-1,-1,-1).}Now you can simply call "detectFaceInImage" whenever you want to find a face in an image. You also need to specify the face classifier that OpenCV should use to detect the face. For example, OpenCV comes with several different classifiers for frontal face detection, as well as some profile faces (side view), eye detection, nose detection, mouth detection, whole body detection, etc. You can actually use this function with any of these other detectors if you want, or even create your own custom detector such as for car or person detection (read here), but since frontal face detection is the only one that is very reliable, it is the only one I will discuss.For frontal face detection, you can chose one of these Haar Cascade Classifiers that come with OpenCV (in the "data\haarcascades\" folder):"haarcascade_frontalface_default.xml""haarcascade_frontalface_alt.xml""haarcascade_frontalface_alt2.xml""haarcascade_frontalface_alt_tree.xml"Each one will give slightly different results depending on your environment, so you could even use all of them and combine the results together (if you want the most detections). There are also some more eye, head, mouth and nose detectors in the downloads section of Modesto's page.So you could do this in your program for face detection:// Haar Cascade file, used for Face Detection.char *faceCascadeFilename ="haarcascade_frontalface_alt.xml";// Load the HaarCascade classifier for face detection.CvHaarClassifierCascade* faceCascade;faceCascade = (CvHaarClassifierCascade*)cvLoad(faceCascadeFilename, 0, 0, 0);if( !faceCascade ) {printf("Couldnt load Face detector '%s'\n", faceCascadeFilename);exit(1);}// Grab the next frame from the camera.IplImage *inputImg = cvQueryFrame(camera);// Perform face detection on the input image, using the given Haar classifierCvRect faceRect = detectFaceInImage(inputImg, faceCascade);// Make sure a valid face was detected.if (faceRect.width > 0) {printf("Detected a face at (%d,%d)!\n", faceRect.x, faceRect.y);}.... Use 'faceRect' and 'inputImg' ....// Free the Face Detector resources when the program is finished cvReleaseHaarClassifierCascade( &cascade );How to preprocess facial images for Face Recognition:Now that you have detected a face, you can use that face image for Face Recognition. However, if you tried to simply perform face recognition directly on a normal photo image, you will probably get less than 10% accuracy!It is extremely important to apply various image pre-processing techniques to standardize the images that you supply to a face recognition system. Most face recognition algorithms are extremely sensitive to lighting conditions, so that if it was trained to recognize a person when they are in a dark room, it probably wont recognize them in a bright room, etc. This problem is referred to as "lumination dependent", and there are also many other issues, such as the face should also be in a very consistent position within the images (such as the eyes being in the same pixel coordinates), consistent size, rotation angle, hair and makeup, emotion (smiling, angry, etc), position of lights (to the left or above, etc). This is why it is so important to use a good image preprocessing filters before applying face recognition. You should also do things like removing the pixels around the face that aren't used, such as with an elliptical mask to only show the inner face region, not the hair and image background, since they change more than the face does.For simplicity, the face recognition system I will show you is Eigenfaces using greyscale images. So I will show you how to easily convert color images to greyscale (also called 'grayscale'), and then easily apply Histogram Equalization as a very simplemethod of automatically standardizing the brightness and contrast of your facial images. For better results, you could use color face recognition (ideally with color histogram fitting in HSV or another color space instead of RGB), or apply more processing stages such as edge enhancement, contour detection, motion detection, etc. Also, this code is resizing images to a standard size, but this might change the aspect ratio of the face. You can read my tutorial HERE on how to resize an image while keeping its aspect ratio the same.Here you can see an example of this preprocessing stage:Here is some basic code to convert from a RGB or greyscale input image to a greyscale image, resize to a consistent dimension, then apply Histogram Equalization for consistent brightness and contrast:// Either convert the image to greyscale, or use the existing greyscale image. IplImage *imageGrey;if (imageSrc->nChannels == 3) {imageGrey = cvCreateImage( cvGetSize(imageSrc), IPL_DEPTH_8U, 1 );// Convert from RGB (actually it is BGR) to Greyscale.cvCvtColor( imageSrc, imageGrey, CV_BGR2GRAY );}else {// Just use the input image, since it is already Greyscale.imageGrey = imageSrc;}// Resize the image to be a consistent size, even if the aspect ratio changes.IplImage *imageProcessed;imageProcessed = cvCreateImage(cvSize(width, height), IPL_DEPTH_8U, 1);// Make the image a fixed size. // CV_INTER_CUBIC or CV_INTER_LINEAR is good for enlarging, and // CV_INTER_AREA is good for shrinking / decimation, but bad at enlarging.cvResize(imageGrey, imageProcessed, CV_INTER_LINEAR);// Give the image a standard brightness and contrast.cvEqualizeHist(imageProcessed, imageProcessed);..... Use 'imageProcessed' for Face Recognition ....if (imageGrey)cvReleaseImage(&imageGrey);if (imageProcessed)cvReleaseImage(&imageProcessed);How Eigenfaces can be used for Face Recognition:Now that you have a pre-processed facial image, you can perform Eigenfaces (PCA) for Face Recognition. OpenCV comes with the function "cvEigenDecomposite()", which performs the PCA operation, however you need a database (training set) of images for it to know how to recognize each of your people.So you should collect a group of preprocessed facial images of each person you want to recognize. For example, if you want to recognize someone from a class of 10 students, then you could store 20 photos of each person, for a total of 200 preprocessed facial images of the same size (say 100x100 pixels).The theory of Eigenfaces is explained in the two Face Recognition with Eigenface articles in Servo Magazine, but I will also attempt to explain it here.Use "Principal Component Analysis" to convert all your 200 training images into a set of "Eigenfaces" that represent the main differences between the training images. First it will find the "average face image" of your images by getting the mean value of each pixel. Then the eigenfaces are calculated in comparison to this average face, where the first eigenface is the most dominant face differences, and the second eigenface is the second most dominant face differences, and so on, until you have about 50 eigenfaces that represent most of the differences in all the training set images.In these example images above you can see the average face and the first and last eigenfaces that were generated from a collection of 30 images each of 4 people. Notice that the average face will show the smooth face structure of a generic person, the first few eigenfaces will show some dominant features of faces, and the last eigenfaces (eg: Eigenface 119) are mainly image noise. You can see the first 32 eigenfaces in the image below.Explanation of Face Recognition using Principal Component Analysis:To explain Eigenfaces (Principal Component Analysis) in simple terms, Eigenfaces figures out the main differences between all the training images, and then how to represent each training image using a combination of those differences.So for example, one of the training images might be made up of:(averageFace) + (13.5% of eigenface0) - (34.3% of eigenface1) + (4.7% of eigenface2) + ... + (0.0% of eigenface199).Once it has figured this out, it can think of that training image as the 200 ratios: {13.5, -34.3, 4.7, ..., 0.0}.It is indeed possible to generate the training image back from the 200 ratios by multiplying the ratios with the eigenface images, and adding the average face. But since many of the last eigenfaces will be image noise or wont contribute much to the image, this list of ratios can be reduced to just the most dominant ones, such as the first 30 numbers, without effecting the image quality much. So now its possible to represent all 200 training images using just 30 eigenface images, the average face image, and a list of 30 ratios for each of the 200 training images.Interestingly, this means that we have found a way to compress the 200 images into just 31 images plus a bit of extra data, without loosing much image quality. But this tutorial is about face recognition, not image compression, so we will ignore that :-)To recognize a person in a new image, it can apply the same PCA calculations to find 200 ratios for representing the input image using the same 200 eigenfaces. And once again it can just keep the first 30 ratios and ignore the rest as they are less important. It can then search through its list of ratios for each of its 20 known people in its database, to see who has their top 30 ratios that are most similar to the 30 ratios for the input image. This is basically a method of checking which training image is most similar to the input image, out of the whole 200 training images that were supplied. Implementing Offline Training:For implementation of offline training, where files are used as input and output through the command-line, I am using a similar method as the Face Recognition with Eigenface implementation in Servo Magazine, so you should read that article first, but I have made a few slight changes.Basically, to create a facerec database from training images, you create a text file that lists the image files and which person each image file represents.For example, you could put this into a text file called "4_images_of_2_people.txt":1 Shervindata\Shervin\Shervin1.bmp1 Shervindata\Shervin\Shervin2.bmp1 Shervindata\Shervin\Shervin3.bmp1 Shervindata\Shervin\Shervin4.bmp2 Chandandata\Chandan\Chandan1.bmp2 Chandandata\Chandan\Chandan2.bmp2 Chandandata\Chandan\Chandan3.bmp2 Chandandata\Chandan\Chandan4.bmpThis will tell the program that person 1 is named "Shervin", and the 4 preprocessedfacial photos of Shervin are in the "data\Shervin" folder, and person 2 is called "Chandan" with 4 images in the "data\Chandan" folder. The program can then loaded them all into an array of images using the function "loadFaceImgArray()". Note that for simplicity, it doesn't allow spaces or special characters in the person's name, so you might want to enable this, or replace spaces in a person's name with underscores (such as Shervin_Emami).To create the database from these loaded images, you use OpenCV's "cvCalcEigenObjects()" and "cvEigenDecomposite()" functions, eg:// Tell PCA to quit when it has enough eigenfaces.CvTermCriteria calcLimit = cvTermCriteria( CV_TERMCRIT_ITER, nEigens, 1);// Compute average image, eigenvectors (eigenfaces) and eigenvalues (ratios).cvCalcEigenObjects(nTrainFaces, (void*)faceImgArr, (void*)eigenVectArr, CV_EIGOBJ_NO_CALLBACK, 0, 0, &calcLimit,pAvgTrainImg, eigenValMat->data.fl);// Normalize the matrix of eigenvalues.cvNormalize(eigenValMat, eigenValMat, 1, 0, CV_L1, 0);// Project each training image onto the PCA subspace.CvMat projectedTrainFaceMat = cvCreateMat( nTrainFaces, nEigens, CV_32FC1 );int offset = projectedTrainFaceMat->step / sizeof(float);for(int i=0; i<nTrainFaces; i++) {cvEigenDecomposite(faceImgArr[i], nEigens, eigenVectArr, 0, 0,pAvgTrainImg, projectedTrainFaceMat->data.fl + i*offset);}You now have:the average image "pAvgTrainImg",the array of eigenface images "eigenVectArr[]" (eg: 200 eigenfaces if you used nEigens=200 training images),the matrix of eigenvalues (eigenface ratios) "projectedTrainFaceMat" of each training image.These can now be stored into a file, which will be the face recognition database. The function "storeTrainingData()" in the code will store this data into the file "facedata.xml", which can be reloaded anytime to recognize people that it has beentrained for. There is also a function "storeEigenfaceImages()" in the code, to generate the images shown earlier, of the average face image to "out_averageImage.bmp" and eigenfaces to "out_eigenfaces.bmp".Implementing Offline Recognition:For implementation of the offline recognition stage, where the face recognition system will try to recognize who is the face in several photos from a list in a text file, I am also using an extension of the Face Recognition with Eigenface implementation in Servo Magazine.The same sort of text file that is used for offline training can also be used for offline recognition. The text file lists the images that should be tested, as well as the correct person in that image. The program can then try to recognize who is in each photo, and check the correct value in the input file to see whether it was correct or not, for generating statistics of its own accuracy.The implementation of the offline face recognition is almost the same as offline training:The list of image files (preprocessed faces) and names are loaded into an array of images, from the text file that is now used for recognition testing (instead of training). This is performed in code by "loadFaceImgArray()".The average face, eigenfaces and eigenvalues (ratios) are loaded from the face recognition database file "facedata.xml", by the function "loadTrainingData()".Each input image is projected onto the PCA subspace using the OpenCV function "cvEigenDecomposite()", to see what ratio of eigenfaces is best for representing this input image.But now that it has the eigenvalues (ratios of eigenface images) to represent the input image, it looks for the original training image that had the most similar ratios. This is done mathematically in the function "findNearestNeighbor()" using the "Euclidean Distance", but basically it checks how similar the input image is to each training image, and finds the most similar one: the one with the least distance in Euclidean Space. As mentioned in the Servo Magazine article, you might get better results if you use the Mahalanobis space (define USE_MAHALANOBIS_DISTANCE in the code).The distance between the input image and most similar training image is used to determine the "confidence" value, to be used as a guide of whether someone wasactually recognized or not. A confidence of 1.0 would mean a good match, and a confidence of 0.0 or negative would mean a bad match. But beware that the confidence formula I use in the code is just a very basic confidence metric that isn't necessarily too reliable, but I figured that most people would like to see a rough confidence value. You may find that it gives misleading values for your images and so you can disable it if you want (eg: set the confidence always to 1.0).Once it knows which training image is most similar to the input image, and assuming the confidence value is not too low (it should be atleast 0.6 or higher), then it has figured out who that person is, in other words, it has recognized that person! Implementing Realtime Recognition from a Camera:It is very easy to use a webcam stream as input to the face recognition system instead of a file list. Basically you just need to grab frames from a camera instead of from a file, and you run forever until the user wants to quit, instead of just running until the file list has run out. OpenCV provides the 'cvCreateCameraCapture()' function (also known as 'cvCaptureFromCAM()') for this.Grabbing frames from a webcam can be implemented easily using this function:// Grab the next camera frame. Waits until the next frame is ready, and // provides direct access to it, so do NOT modify or free the returned image! // Will automatically initialize the camera on the first frame.IplImage* getCameraFrame(CvCapture* &camera){IplImage *frame;int w, h;// If the camera hasn't been initialized, then open it.if (!camera) {printf("Acessing the camera ...\n");camera = cvCreateCameraCapture( 0 );if (!camera) {printf("Couldn't access the camera.\n");exit(1);}// Try to set the camera resolution to 320 x 240.cvSetCaptureProperty(camera, CV_CAP_PROP_FRAME_WIDTH, 320);cvSetCaptureProperty(camera, CV_CAP_PROP_FRAME_HEIGHT, 240);// Get the first frame, to make sure the camera is initialized.frame = cvQueryFrame( camera );if (frame) {w = frame->width;h = frame->height;printf("Got the camera at %dx%d resolution.\n", w, h);}// Wait a little, so that the camera can auto-adjust its brightness.Sleep(1000); // (in milliseconds)}// Wait until the next camera frame is ready, then grab it.frame = cvQueryFrame( camera );if (!frame) {printf("Couldn't grab a camera frame.\n");exit(1);}return frame;}This function can be used like this:CvCapture* camera = 0; // The camera device.while ( cvWaitKey(10) != 27 ) { // Quit on "Escape" key.IplImage *frame = getCameraFrame(camera);...}// Free the camera.cvReleaseCapture( &camera );Note that if you are developing for MS Windows, you can grab camera frames twice as fast as this code by using the videoInput Library v0.1995 by Theo Watson. It uses hardware-accelerated DirectShow, whereas OpenCV uses VFW that hasn't changed in 15 years!Putting together all the parts that I have explained so far, the face recognition systemruns as follows:Grab a frame from the camera (as I mentioned here).Convert the color frame to greyscale (as I mentioned here).Detect a face within the greyscale camera frame (as I mentioned here).Crop the frame to just show the face region (using cvSetImageROI() and cvCopyImage()).Preprocess the face image (as I mentioned here).Recognize the person in the image (as I mentioned here).Implementing Online Training from a Camera:Now you have a way to recognize people in realtime using a camera, but to learn new faces you would have to shutdown the program, save the camera images as image files, update the training images list, use the offline training method from the command-line, and then run the program again in realtime camera mode. So in fact, this is exactly what you can do programmatically to perform online training from a camera in realtime!So here is the easiest way to add a new person to the face recognition database from the camera stream without shutting down the program:Collect a bunch of photos from the camera (preprocessed facial images), possibly while you are performing face recognition also.Save the collected face images as image files onto the hard-disk using cvSaveImage().Add the filename of each face image onto the end of the training images list file (the text file that is used for offline training).Once you are ready for online training the new images (such as once you have 20 faces, or when the user says that they are ready), you "retrain" the database from all the image files. The text file listing the training image files has the new images added to it, and the images are stored as image files on the computer, so online training works just like it did in offline training.But before retraining, it is important to free any resources that were being used, and re-initialize the variables, so that it behaves as if you shutdown the program and restarted. For example, after the images are stored as files and added to the training list text file, you should free the arrays of eigenfaces, before doing the equivalent of offline training (which involves loading all the images from the training list file, then findingthe eigenfaces and ratios of the new training set using PCA).This method of online training is fairly inefficient, because if there was 50 people in the training set and you add one more person, then it will train again for all 51 people, which is bad because the amount of time for training is exponential with more users or training images. But if you are just dealing with a few hundred training images in total then it shouldn't take more than a few seconds.Download OnlineFaceRec:The software and source-code is available here (open-source freeware), to use on Windows, Mac, Linux, iPhone, etc as you wish for educational or personal purposes, but NOT for commercial, criminal-detection, or military purposes (because this code is way too simple & unreliable for critical applications such as criminal detection, and also I no longer support any military).Click here to download "OnlineFaceRec" for Windows: onlineFaceRec.zip(0.07MB file including C/C++ source code, VS2008 project files and the compiled Win32 program, created 4th Feb 2012).Click here to download "OnlineFaceRec" for Linux: onlineFaceRec_Linux.zip(0.003MB file including C/C++ source code and a compiled Linux program, created 30th Dec 2011).If you dont have the OpenCV 2.0 SDK then you can just get the Win32 DLLs and HaarCascade for running this program (including 'cvaux200.dll' and 'haarcascade_frontalface_alt.xml'): onlineFaceRec_OpenCVbinaries.7z (1.7MB 7-Zip file).And if you want to run the program but dont have the Visual Studio 2008 runtime installed then you can just get the Win32 DLLs ('msvcr90.dll', etc): MS_VC90_CRT.7z (0.4MB 7-Zip file).To open Zip or 7z files you can use the freeware 7-Zip program (better than WinZip and WinRar in my opinion) from HERE.The code was tested with MS Visual Studio 2008 using OpenCV v2.0 and on Linux with GCC 4.2 using OpenCV v2.3.1, but I assume it works with other versions & compilers fairly easily, and it should work the same in all versions of OpenCV before v2.2. Students also ported this code to Dev-C++ athttps:///projects/facerec/.There are two different ways you can use this system:As a realtime program that performs face detection and online face recognition from a web camera.As a command-line program to perform offline face recognition using text files, just like the eigenface program in Servo Magazine.How to use the realtime webcam FaceRec system:If you have a webcam plugged in, then you should be able to test this program by just double-clicking the EXE file in Windows (or compile the code and run it if you are using Linux or Mac). Hit the Escape key on the GUI window when you want to quit the program.After a few seconds it should show the camera image, with the detected face highlighted. But at first it wont have anyone in its face rec database, so you will need to create it by entering a few keys. Beware that to use the keyboard, you have to click on the DOS console window before typing anything (because if the OpenCV window is highlighted then the code wont know what you typed).In the console window, hit the 'n' key on your keyboard when a person is ready for training. This will add a new person to the facerec database. Type in the person's name (without any spaces) and hit Enter.It will begin to automatically store all the processed frontal faces that it sees. Get a person to move their head around a bit until it has stored about 20 faces of them. (The facial images are stored as PGM files in the "data" folder, and their names are appended to the text file "train.txt").Get the person in front of the camera to move around a little and move their face a little, so that there will be some variance in the training images.Then when you have enough detected faces for that person, ideally more than 30 for each person, hit the 't' key in the console window to begin training on the images that were just collected. It will then pause for about 5-30 seconds (depending on how many faces and people are in the database), and finally continue once it has retrained with the extra person. The database file is called "facedata.xml".It should print the person's name in the console whenever it recognizes them. Repeat this again from step 1 whenever you want to add a new person, even after you have shutdown the program.。

人脸识别英文作文

人脸识别英文作文Face recognition technology has become increasingly popular in recent years. It is a fascinating and controversial topic that has sparked debates anddiscussions around the world. The ability to identify and verify individuals based on their facial features has numerous applications and implications, both positive and negative.The use of face recognition technology in security systems is one of its most widely known applications. It allows for quick and accurate identification of individuals, enhancing the efficiency and effectiveness of security measures. This technology has been adopted in airports, government buildings, and even smartphones, providing a convenient and secure way to access restricted areas or personal devices.Another interesting application of face recognition technology is in the field of entertainment. Many amusementparks and attractions now use this technology to create personalized experiences for visitors. By scanning their faces, the system can identify individuals and tailor the attractions accordingly, providing a unique and immersive experience.In addition to its practical applications, face recognition technology has also raised concerns about privacy and personal data protection. The ability to capture and store facial images raises questions about who has access to this information and how it can be used. People worry that their identities could be stolen or misused, leading to potential harm or discrimination.Furthermore, the accuracy and reliability of face recognition technology have been subjects of debate. Some argue that the technology is not foolproof and can beeasily tricked or manipulated. Others believe that the algorithms used in these systems are biased and may produce false positives or negatives, leading to wrongful identifications or exclusions.Despite the controversies and concerns surrounding face recognition technology, its potential for positive impact cannot be ignored. It has the ability to revolutionize various industries, from security to healthcare and beyond. However, it is crucial to strike a balance between the benefits and risks associated with its use, ensuring that proper regulations and safeguards are in place to protect individuals' rights and privacy.In conclusion, face recognition technology is apowerful tool with a wide range of applications. Itsability to identify and verify individuals based on their facial features has both positive and negative implications. While it enhances security and provides personalized experiences, it also raises concerns about privacy and accuracy. It is important to carefully consider the ethical and legal implications of its use and ensure that it is implemented in a responsible and transparent manner.。

人脸识别在中国的应用在哪里英语作文

人脸识别在中国的应用在哪里英语作文Facial recognition technology has been rapidly advancing in recent years and has found numerous applications across various industries in China. This powerful technology has the ability to identify and verify individuals by analyzing their unique facial features, making it a valuable tool in areas such as security, surveillance, and personalized services. In this essay, we will explore the diverse applications of facial recognition in China and examine its impact on the country's technological landscape.One of the primary applications of facial recognition in China is in the field of public security and law enforcement. The Chinese government has invested heavily in the development of large-scale surveillance systems that utilize facial recognition technology. These systems are integrated into the country's extensive network of CCTV cameras, allowing authorities to track and identify individuals in real-time. This technology has been particularly useful in identifying and apprehending criminal suspects, as well as in monitoring potential security threats.Furthermore, facial recognition has been increasingly adopted in the transportation sector in China. Many public transportation systems, such as subway and train stations, have implemented facial recognition-based payment systems. Passengers can simply walk through designated gates and have their identities verified, eliminating the need for physical tickets or cards. This not only enhances the efficiency of the transportation system but also provides a more convenient and seamless experience for commuters.Another area where facial recognition has found widespread application in China is in the retail and e-commerce industries. Retailers are leveraging this technology to enhance customer experience and improve operational efficiency. Facial recognition systems can be used to identify and greet regular customers, provide personalized product recommendations, and even detect and prevent theft. In the e-commerce sector, facial recognition is being integrated into mobile payment solutions, allowing customers to make purchases securely and conveniently using their facial features.The healthcare industry in China has also benefited from the advancements in facial recognition technology. Hospitals and clinics are using this technology to streamline patient check-in and identification processes, reducing wait times and improving overall patient experience. Additionally, facial recognition is being explored for use in remote healthcare consultations, where patients can beidentified and connected with their medical records seamlessly.Beyond these practical applications, facial recognition technology is also being utilized in the entertainment and social media sectors in China. Platforms like social media and online gaming are integrating facial recognition features to enhance user engagement and personalization. Users can, for example, unlock exclusive features or access personalized content based on their facial characteristics.The widespread adoption of facial recognition in China has not been without its challenges and controversies. Concerns have been raised about privacy and data security, as the collection and storage of biometric data can potentially be misused or abused. The Chinese government has faced criticism for its extensive use of facial recognition-based surveillance systems, which some consider a violation of individual privacy rights.Despite these concerns, the Chinese government has continued to invest heavily in the development and implementation of facial recognition technology. The country's large population, extensive infrastructure, and the government's focus on technological innovation have all contributed to the rapid growth of this industry.In conclusion, the application of facial recognition technology in China has been diverse and far-reaching. From public security andtransportation to retail and healthcare, this powerful technology has transformed numerous industries and has become an integral part of the country's technological landscape. As the technology continues to evolve and become more sophisticated, it will be crucial for policymakers, industry leaders, and the public to address the ethical and privacy concerns associated with its use, ensuring that the benefits of facial recognition are balanced with the protection of individual rights and freedoms.。

人脸识别外文翻译参考文献

人脸识别外文翻译参考文献(文档含中英文对照即英文原文和中文翻译)译文：基于PAC的实时人脸检测和跟踪方法摘要：这篇文章提出了复杂背景条件下，实现实时人脸检测和跟踪的一种方法。

这种方法是以主要成分分析技术为基础的。

为了实现人脸的检测，首先，我们要用一个肤色模型和一些动作信息(如：姿势、手势、眼色)。

然后，使用PAC技术检测这些被检验的区域，从而判定人脸真正的位置。

而人脸跟踪基于欧几里德（Euclidian）距离的，其中欧几里德距离在位于以前被跟踪的人脸和最近被检测的人脸之间的特征空间中。

用于人脸跟踪的摄像控制器以这样的方法工作：利用平衡/（pan/tilt）平台，把被检测的人脸区域控制在屏幕的中央。

这个方法还可以扩展到其他的系统中去，例如电信会议、入侵者检查系统等等。

1.引言视频信号处理有许多应用，例如鉴于通讯可视化的电信会议，为残疾人服务的唇读系统。

在上面提到的许多系统中，人脸的检测喝跟踪视必不可缺的组成部分。

在本文中，涉及到一些实时的人脸区域跟踪[1-3]。

一般来说，根据跟踪角度的不同，可以把跟踪方法分为两类。

有一部分人把人脸跟踪分为基于识别的跟踪喝基于动作的跟踪，而其他一部分人则把人脸跟踪分为基于边缘的跟踪和基于区域的跟踪[4]。

基于识别的跟踪是真正地以对象识别技术为基础的，而跟踪系统的性能是受到识别方法的效率的限制。

基于动作的跟踪是依赖于动作检测技术，且该技术可以被分成视频流（optical flow）的（检测）方法和动作—能量（motion－energy）的（检测）方法。

基于边缘的（跟踪）方法用于跟踪一幅图像序列的边缘，而这些边缘通常是主要对象的边界线。

然而，因为被跟踪的对象必须在色彩和光照条件下显示出明显的边缘变化，所以这些方法会遭遇到彩色和光照的变化。

此外，当一幅图像的背景有很明显的边缘时，（跟踪方法）很难提供可靠的（跟踪）结果。

当前很多的文献都涉及到的这类方法时源于Kass et al.在蛇形汇率波动[5]的成就。

人脸识别外文文献

Method of Face Recognition Based on Red-BlackWavelet Transform and PCAYuqing He, Huan He， and Hongying YangDepartment of Opto-Electronic Engineering，Beijing Institute of Technology, Beijing， P.R. China, 10008120701170@。

cnAbstract。

With the development of the man—machine interface and the recogni—tion technology， face recognition has became one of the most important research aspects in the biological features recognition domain. Nowadays, PCA（Principal Components Analysis） has applied in recognition based on many face database and achieved good results. However， PCA has its limitations: the large volume of computing and the low distinction ability。

In view of these limitations, this paper puts forward a face recognition method based on red—black wavelet transform and PCA. The improved histogram equalization is used to realize image pre-processing in order to compensate the illumination. Then, appling the red—black wavelet sub—band which contains the information of the original image to extract the feature and do matching。

人脸识别英文文献

A Parallel Framework for Multilayer Perceptron for Human FaceRecognitionDebotosh Bhattacharjee debotosh@ Reader,Department of Computer Science and Engineering,Jadavpur University,Kolkata- 700032, India.Mrinal Kanti Bhowmik mkb_cse@yahoo.co.in Lecturer,Department of Computer Science and Engineering,Tripura University (A Central University),Suryamaninagar- 799130, Tripura, India.Mita Nasipuri mitanasipuri@ Professor,Department of Computer Science and Engineering,Jadavpur University,Kolkata- 700032, India.Dipak Kumar Basu dipakkbasu@ Professor, AICTE Emeritus Fellow,Department of Computer Science and Engineering,Jadavpur University,Kolkata- 700032, India.Mahantapas Kundu mkundu@cse.jdvu.ac.in Professor,Department of Computer Science and Engineering,Jadavpur University,Kolkata- 700032, India.AbstractArtificial neural networks have already shown their success in face recognition and similar complex pattern recognition tasks. However, a major disadvantage of the technique is that it is extremely slow during training for larger classes and hence not suitable for real-time complex problems such as pattern recognition. This is an attempt to develop a parallel framework for the training algorithm of a perceptron. In this paper, two general architectures for a Multilayer Perceptron (MLP) have been demonstrated. The first architecture is All-Class-in-One-Network (ACON) where all the classes are placed in a single network and the second one is One-Class-in-One-Network (OCON) where an individual single network is responsible for each and every class. Capabilities of these two architectures were compared and verified in solving human face recognition, which is a complex pattern recognition task where several factors affect the recognition performance like pose variations, facial expression changes, occlusions, and most importantly illumination changes. Both the structures wereimplemented and tested for face recognition purpose and experimental results show that the OCON structure performs better than the generally used ACON ones in term of training convergence speed of the network. Unlike the conventional sequential approach of training the neural networks, the OCON technique may be implemented by training all the classes of the face images simultaneously.Keywords:Artificial Neural Network, Network architecture, All-Class-in-One-Network (ACON), One-Class-in-One-Network (OCON), PCA, Multilayer Perceptron, Face recognition.1. INTRODUCTIONNeural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. A trained neural network can be thought of as an "expert" in the category of information it has been given to analyze [1]. This proposed work describes the way by which an Artificial Neural Network (ANN) can be designed and implemented over a parallel or distributed environment to reduce its training time. Generally, an ANN goes through three different steps: training of the network, testing of it and final use of it. The final structure of an ANN is generally found out experimentally. This requires huge amount of computation. Moreover, the training time of an ANN is very large, when the classes are linearly non-separable and overlapping in nature. Therefore, to save computation time and in order to achieve good response time the obvious choice is either a high-end machine or a system which is collection of machines with low computational power.In this work, we consider multilayer perceptron (MLP) for human face recognition, which has many real time applications starting from automatic daily attendance checking, allowing the authorized people to enter into highly secured area, in detecting and preventing criminals and so on. For all these cases, response time is very critical. Face recognition has the benefit of being passive, nonintrusive system for verifying personal identity. The techniques used in the best face recognition systems may depend on the application of the system.Human face recognition is a very complex pattern recognition problem, altogether. There is no stability in the input pattern due to different expressions, adornments in the input images. Sometimes, distinguishing features appear similar and produce a very complex situation to take decision. Also, there are several other that make the face recognition task complicated. Some of them are given below.a) Background of the face image can be a complex pattern or almost same as the color of theface.b) Different illumination level, at different parts of the image.c) Direction of illumination may vary.d) Tilting of face.e) Rotation of face with different angle.f) Presence/absence of beard and/or moustacheg) Presence/Absence of spectacle/glasses.h) Change in expressions such as disgust, sadness, happiness, fear, anger, surprise etc.i) Deliberate change in color of the skin and/or hair to disguise the designed system.From above discussion it can now be claimed that the face recognition problem along with face detection, is very complex in nature. To solve it, we require some complex neural network, which takes large amount of time to finalize its structure and also to settle its parameters.In this work, a different architecture has been used to train a multilayer perceptron in faster way. Instead of placing all the classes in a single network, individual networks are used for each of theclasses. Due to lesser number of samples and conflicts in the belongingness of patterns to their respective classes, a later model appears to be faster in comparison to former.2. ARTIFICIAL NEURAL NETWORKArtificial neural networks (ANN) have been developed as generalizations of mathematical models of biological nervous systems. A first wave of interest in neural networks (also known as connectionist models or parallel distributed processing) emerged after the introduction of simplified neurons by McCulloch and Pitts (1943).The basic processing elements of neural networks are called artificial neurons, or simply neurons or nodes. In a simplified mathematical model of the neuron, the effects of the synapses are represented by connection weights that modulate the effect of the associated input signals, and the nonlinear characteristic exhibited by neurons is represented by a transfer function. The neuron impulse is then computed as the weighted sum of the input signals, transformed by the transfer function. The learning capability of an artificial neuron is achieved by adjusting the weights in accordance to the chosen learning algorithm. A neural network has to be configured such that the application of a set of inputs produces the desired set of outputs. Various methods to set the strengths of the connections exist. One way is to set the weights explicitly, using a priori knowledge. Another way is to train the neural network by feeding it teaching patterns and letting it change its weights according to some learning rule. The learning situations in neural networks may be classified into three distinct sorts. These are supervised learning, unsupervised learning, and reinforcement learning. In supervised learning,an input vector is presented at the inputs together with a set of desired responses, one for each node, at the output layer. A forward pass is done, and the errors or discrepancies between the desired and actual response for each node in the output layer are found. These are then used to determine weight changes in the net according to the prevailing learning rule. The term supervised originates from the fact that the desired signals on individual output nodes are provided by an external teacher [3]. Feed-forward networks had already been used successfully for human face recognition. Feed-forward means that there is no feedback to the input. Similar to the way that human beings learn from mistakes, neural networks also could learn from their mistakes by giving feedback to the input patterns. This kind of feedback would be used to reconstruct the input patterns and make them free from error; thus increasing the performance of the neural networks. Of course, it is very complex to construct such types of neural networks. These kinds of networks are called as auto associative neural networks. As the name implies, they use back-propagation algorithms. One of the main problems associated with back-propagation algorithms is local minima. In addition, neural networks have issues associated with learning speed, architecture selection, feature representation, modularity and scaling. Though there are problems and difficulties, the potential advantages of neural networks are vast. Pattern recognition can be done both in normal computers and neural networks. Computers use conventional arithmetic algorithms to detect whether the given pattern matches an existing one. It is a straightforward method. It will say either yes or no. It does not tolerate noisy patterns. On the other hand, neural networks can tolerate noise and, if trained properly, will respond correctly for unknown patterns. Neural networks may not perform miracles, but if constructed with the proper architecture and trained correctly with good data, they will give amazing results, not only in pattern recognition but also in other scientific and commercial applications [4].2A. Network ArchitectureThe computing world has a lot to gain from neural networks. Their ability to learn by example makes them very flexible and powerful. Once a network is trained properly there is no need to devise an algorithm in order to perform a specific task; i.e. no need to understand the internal mechanisms of that task. The architecture of any neural networks generally used is All-Class-in-One-Network (ACON), where all the classes are lumped into one super-network. Hence, the implementation of such ACON structure in parallel environment is not possible. Also, the ACON structure has some disadvantages like the super-network has the burden to simultaneously satisfy all the error constraints by which the number of nodes in the hidden layers tends to be large. The structure of the network is All-Classes-in-One-Network (ACON), shown in Figure 1(a) where one single network is designed to classify all the classes but in One-Class-in-One-Network(OCON), shown in Figure 1(b) a single network is dedicated to recognize one particular class. For each class, a network is created with all the training samples of that class as positive examples, called the class-one, and the negative examples for that class i.e. exemplars from other classes, constitute the class-two. Thus, this classification problem is a two-class partitioning problem. So far, as implementation is concerned, the structure of the network remains the same for all classes and only the weights vary. As the network remains same, weights are kept in separate files and the identification of input image is made on the basis of feature vector and stored weights applied to the network one by one, for all the classes.(a)(b)Figure 1: a) All-Classes-in-One-Network (ACON) b) One-Class-in-One-Network (OCON). Empirical results confirm that the convergence rate of ACON degrades drastically with respect to the network size because the training of hidden units is influenced by (potentially conflicting) signals from different teachers. If the topology is changed to One Class in One Network (OCON) structure, where one sub-network is designated and responsible for one class only then each sub-network specializes in distinguishing its own class from the others. So, the number of hidden units is usually small.2B. Training of an ANNIn the training phase the main goal is to utilize the resources as much as possible and speed-up the computation process. Hence, the computation involved in training is distributed over the system to reduce response time. The training procedure can be given as:(1) Retrieve the topology of the neural network given by the user,(2) Initialize required parameters and weight vector necessary to train the network,(3) Train the network as per network topology and available parameters for all exemplars of different classes,(4) Run the network with test vectors to test the classification ability,(5) If the result found from step 4 is not satisfactory, loop back to step 2 to change the parameters like learning parameter, momentum, number of iteration or even the weight vector,(6) If the testing results do not improve by step 5, then go back to step 1,(7) The best possible (optimal) topology and associated parameters found in step 5 and step 6 are stored.Although we have parallel systems already in use but some problems cannot exploit advantages of these systems because of their inherent sequential execution characteristics. Therefore, it is necessary to find an equivalent algorithm, which is executable in parallel.In case of OCON, different individual small networks with least amount of load, which are responsible for different classes (e.g. k classes), can easily be trained in k different processors and the training time must reduce drastically. To fit into this parallel framework previous training procedure can be modified as follows:(1) Retrieve the topology of the neural network given by the user,(2) Initialize required parameters and weight vector necessary to train the network,(3) Distribute all the classes (say k) to available processors (possibly k) by some optimal process allocation algorithm,(4) Ensure the retrieval the exemplar vectors of respective classes by the corresponding processors,(5) Train the networks as per network topology and available parameters for all exemplars of different classes,(6) Run the networks with test vectors to test the classification ability,(7) If the result found from step 6 is not satisfactory, loop back to step 2 to change the parameters like learning parameter, momentum, number of iteration or even the weight vector,(8) If the testing results do not improve by step 5, then go back to step 1,(9) The best possible (optimal) topology and associated parameters found in step 7 and step 8 are stored,(10) Store weights per class with identification in more than one computer [2].During the training of two different topologies (OCON and ACON), we used total 200 images of 10 different classes and the images are with different poses and also with different illuminations. Sample images used during training are shown Figure 2. We implemented both the topologies using MATLAB. At the time of training of our systems for both the topologies, we set maximum number of possible epochs (or iterations) to 700000. The training stops if the number of iterations exceeds this limit or performance goal is met. Here, performance goal was considered as 10-6. We have taken total 10 different training runs for 10 different classes for OCON and one single training run for ACON for 10 different classes. In case of the OCON networks, performance goal was met for all the 10 different training cases, and also in lesser amount of time than ACON. After the completion of training phase of our two different topologies we tested our both the network using the images of testing class which are not used in training.2C. Testing PhaseDuring testing, the class found in the database with minimum distance does not necessarily stop the testing procedure. Testing is complete after all the registered classes are tested. During testing some points were taken into account, those are:(1) The weights of different classes already available are again distributed in the available computer to test a particular image given as input,(2) The allocation of the tasks to different processors is done based on the testing time and inter-processor communication overhead. The communication overhead should be much less than the testing time for the success of the distribution of testing, and(3) The weight vector of a class matter, not the computer, which has computed it.The testing of a class can be done in any computer as the topology and the weight vector of that class is known. Thus, the system can be fault tolerant [2]. At the time of testing, we used total 200 images. Among 200 images 100 images are taken from the same classes those are used during the training and 100 images from other classes are not used during the training time. In the both topology (ACON and OCON), we have chosen 20 images for testing, in which 10 images from same class those are used during the training as positive exemplars and other 10 images are chosen from other classes of the database as negative exemplars.2D. Performance measurementPerformance of this system can be measured using following parameters:(1) resource sharing: Different terminals remain idle most of the time can be used as a part of this system. Once the weights are finalized anyone in the net, even though not satisfying the optimal testing time criterion, can use it. This can be done through Internet attempting to end the “tyranny of geography”,(2) high reliability: Here we will be concerned with the reliability of the proposed system, not the inherent fault tolerant property of the neural network. Reliability comes from the distribution of computed weights over the system. If any of the computer(or processor) connected to the network goes down then the system works Some applications like security monitoring system, crime prevention system require that the system should work, whatever may be the performance, (3) cost effectiveness: If we use several small personal computers instead of high-end computing machines, we achieve better price/performance ratio,(4) incremental growth: If the number of classes increases, then the complete computation including the additional complexity can be completed without disturbing the existing system. Based on the analysis of performance of our two different topologies, if we see the recognition rates of OCON and ACON in Table 1 and Table 2 OCON is showing better recognition rate than ACON. Comparison in terms of training time can easily be observed in figures 3 (Figure 3 (a) to (k)). In case of OCON, performance goals met for 10 different classes are 9.99999e-007, 1e-006, 9.99999e-007, 9.99998e-007, 1e-006, 9.99998e-007,1e-006, 9.99997e-007, 9.99999e-007 respectively, whereas for ACON it is 0.0100274. Therefore, it is pretty clear that OCON requires less computational time to finalize a network to use.3. PRINCIPAL COMPONENT ANALYSISThe Principal Component Analysis (PCA) [5] [6] [7] uses the entire image to generate a set of features in the both network topology OCON and ACON and does not require the location of individual feature points within the image. We have implemented the PCA transform as a reduced feature extractor in our face recognition system. Here, each of the visual face images is projected into the eigenspace created by the eigenvectors of the covariance matrix of all the training images for both the ACON and OCON networks. Here, we have taken the number of eigenvectors in the eigenspace as 40 because eigenvalues for other eigenvectors are negligible in comparison to the largest eigenvalues.4. EXPERIMENTS RESULTS USING OCON AND ACONThis work has been simulated using MATLAB 7 in a machine of the configuration 2.13GHz Intel Xeon Quad Core Processor and 16 GB of Physical Memory. We have analyzed the performance of our method using YALE B database which is a collection of visual face images with various poses and illumination.4A. YALE Face Database BThis work has been simulated using MATLAB 7 in a machine of the configuration 2.13GHz Intel Xeon Quad Core Processor and 16 GB of Physical Memory. We have analyzed the performance of our method using YALE B database which is a collection of visual face images with various poses and illumination.This database contains 5760 single light source images of 10 subjects each seen under 576 viewing conditions (9 poses x 64 illumination conditions). For every subject in a particular pose, an image with ambient (background) illumination was also captured. Hence, the total number of images is 5850. The total size of the compressed database is about 1GB. The 65 (64 illuminations + 1 ambient) images of a subject in a particular pose have been "tarred" and "gzipped" into a single file. There were 47 (out of 5760) images whose corresponding strobe did not go off. These images basically look like the ambient image of the subject in a particular pose. The images in the database were captured using a purpose-built illumination rig. This rig is fitted with 64 computer controlled strobes. The 64 images of a subject in a particular pose were acquired at camera frame rate (30 frames/second) in about 2 seconds, so there is only small change in head pose and facial expression for those 64 (+1 ambient) images. The image with ambient illumination was captured without a strobe going off. For each subject, images were captured under nine different poses whose relative positions are shown below. Note the pose 0 is the frontal pose. Poses 1, 2, 3, 4, and 5 were about 12 degrees from the camera optical axis (i.e., from Pose 0), while poses 6, 7, and 8 were about 24 degrees. In the Figure 2 sample images of per subject per pose with frontal illumination. Note that the position of a face in an image varies from pose to pose but is fairly constant within the images of a face seen in one of the 9 poses, since the 64 (+1 ambient) images were captured in about 2 seconds. The acquired images are 8-bit (gray scale) captured with a Sony XC-75 camera (with a linear response function) and stored in PGM raw format. The size of each image is 640(w) x 480 (h) [9].In our experiment, we have chosen total 400 images for our experiment purpose. Among them 200 images are taken for training and other 200 images are taken for testing purpose from 10 different classes. In the experiment we use total two different networks: OCON and ACON. All the recognition results of OCON networks are shown in Table 1, and all the recognition results of ACON network are shown in Table 2. During training, total 10 training runs have been executed for 10 different classes. We have completed total 10 different testing for OCON network using 20 images for each experiment. Out of those 20 images, 10 images are taken form the same classes those were used during training, which acts as positive exemplars and rest 10 images are taken from other classes that acts as negative exemplars for that class. In case of OCON, system achieved 100% recognition rate for all the classes. In case of the ACON network, only one network is used for 10 different classes. During the training we achieved 100% as the highest recognition rate, but like OCON network not for all the classes. For ACON network, on an average, 88% recognition rate was achieved.Figure 2: Sample images of YALE B database with different Pose and different illumination.Class Total number oftesting images Number of imagesfrom the trainingclassNumber ofimages fromother classesRecognitionrateClass-1 20 10 10 100% Class-2 20 10 10 100% Class-3 20 10 10 100% Class-4 20 10 10 100% Class-5 20 10 10 100% Class-6 20 10 10 100% Class-7 20 10 10 100% Class-8 20 10 10 100% Class-9 20 10 10 100% Class-10 20 10 10 100%Table 1: Experiments Results for OCON.Class Total number oftesting images Number of imagesfrom the trainingclassNumber ofimages fromother classesRecognitionrateClass - 1 20 10 10 100%Class - 2 20 10 10 100%Class - 3 20 10 10 90%Class - 4 20 10 10 80%Class - 5 20 10 10 80%Class - 6 20 10 10 80%Class - 7 20 10 10 90%Class - 8 20 10 10 100%Class - 9 20 10 10 90%Class-10 20 10 10 70%Table 2: Experiments results for ACON.In the Figure 3, we have shown all the performance measure and reached goal during 10 different training runs in case of OCON network and also one training phase of ACON network.We set highest epochs 700000, but during the training, in case of all the OCON networks, performance goal was met before reaching maximum number of epochs. All the learning rates with required epochs of OCON and ACON networks are shown at column two of Table 3.In case of the OCON network, if we combine all the recognition rates we have the average recognition rate is 100%. But in case of ACON network, 88% is the average recognition rate i.e.we can say that OCON showing better performance, accuracy and speed than ACON. Figure 4 presents a comparative study on ACON and OCON results.Total no. of iterations Learning Rate(lr)Class Figures Network Used 290556 lr > 10-4 Class – 1 Figure 3(a) 248182 lr =10-4 Class – 2 Figure 3(b) 260384 lr =10-5 Class – 3 Figure 3(c) 293279 lr < 10-4 Class - 4 Figure 3(d) 275065 lr =10-4 Class - 5 Figure 3(e) 251642 lr =10-3 Class – 6 Figure 3(f) 273819 lr =10-4 Class – 7 Figure 3(g) 263251 lr < 10-3Class – 8 Figure 3(h) 295986 lr < 10-3 Class – 9 Figure 3(i) 257019 lr > 10-6 Class - 10 Figure 3(j) OCON Highest epochreached(7, 00, 000)Performance goal not met For all Classes (class -1,…,10) Figure 3(k) ACONTable 3: Learning Rate vs. Required Epochs for OCON and ACON.Figure 3 (a) Class – 1 of OCON Network.Figure 3 (b) Class – 2 of OCON Network.Figure 3 (c) Class – 3 of OCON Network.D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. KunduFigure 3 (d) Class – 4 of OCON Network.Figure 3 (e) Class – 5 of Ocon Network.International Journal of Computer Science and Security (IJCSS), Volume (3): Issue (6)11D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. KunduFigure 3 (f) Class – 6 of OCON Network.Figure 3 (g) Class – 7 of OCON Network.International Journal of Computer Science and Security (IJCSS), Volume (3): Issue (6)12D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. KunduFigure 3 (h) Class – 8 of OCON Network.Figure 3 (i) Class – 9 of OCON Network.International Journal of Computer Science and Security (IJCSS), Volume (3): Issue (6)13D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. KunduFigure 3 (j) Class – 10 of OCON Network.3 (k) of ACON Network for all the classes.International Journal of Computer Science and Security (IJCSS), Volume (3): Issue (6)14D. Bhattacharjee, M. K. Bhowmik, M. Nasipuri, D. K. Basu & M. KunduFigure 4: Graphical Representation of all Recognition Rate using OCON and ACON Network. The OCON is an obvious choice in terms of speed-up and resource utilization. The OCON structure of neural network makes it most suitable for incremental training, i.e., network upgrading upon adding/removing memberships. One may argue that compared to ACON structure, the OCON structure is slow in retrieving time when the number of classes is very large. This is not true because, as the number of classes increases, the number of hidden neurons in the ACON structure also tends to be very large. Therefore ACON is slow. Since the computation time of both OCON and ACON increases as number of classes grows, a linear increasing of computation time is expected in case of OCON, which might be exponential in case of ACON.5. CONCLUSIONIn this paper, two general architectures for a Multilayer Perceptron (MLP) have been demonstrated. The first architecture is All-Class-in-One-Network (ACON) where all the classes are placed in a single network and the second one is One-Class-in-One-Network (OCON) where an individual single network is responsible for each and every class. Capabilities of these two architectures were compared and verified in solving human face recognition, which is a complex pattern recognition task where several factors affect the recognition performance like pose variations, facial expression changes, occlusions, and most importantly illumination changes. Both the structures were implemented and tested for face recognition purpose and experimental results show that the OCON structure performs better than the generally used ACON ones in term of training convergence speed of the network. Moreover, the inherent non-parallel nature of ACON has compelled us to use OCON for the complex pattern recognition task like human face recognition.ACKNOWLEDGEMENTSecond author is thankful to the project entitled “Development of Techniques for Human Face Based Online Authentication System Phase-I” sponsored by Department of Information Technology under the Ministry of Communications and Information Technology, New Delhi110003, Government of India Vide No. 12(14)/08-ESD, Dated 27/01/2009 at the Department of Computer Science & Engineering, Tripura University-799130, Tripura (West), India for providingInternational Journal of Computer Science and Security (IJCSS), Volume (3): Issue (6)15。

Paul Viola经典人脸检测算法论文翻译

在检测过程中，整体形式是一个退化决策树，我们称之为“级联”（见图4）。从第一个分类得到的有效结果能触发第二个分类器，也已调整至达到非常高的检测率。再得到一个有效结果使得第二个分类器触发第三个分类器，以此类推。在任何一个点的错误结果都导致子窗口立刻被剔除。
级联阶段的构成首先是利用AdaBoost训练分类器，然后调整阈值使得负误视最大限度地减少。注意，默认AdaBoost的阈值旨在数据过程中产生低错误率。一般而言，一个较低的阈值会产生更高的检测速率和更高的正误视率。
对于人脸检测的任务，由AdaBoost选择的最初的矩形特征是有意义的且容易理解。选定的第一个特征的重点是眼睛区域往往比鼻子和脸颊区域更黑暗（见图3）。此特征的检测子窗口相对较大，并且某种程度上不受面部大小和位置的影响。第二个特征选择依赖于眼睛的所在位置比鼻梁更暗。
这两个特点显示在最上面一行，然后一个典型的调试面部叠加在底部一行。第一个特点，测量眼睛部区域和上脸颊地区的强烈程度的区别。该特征利用了眼睛部区域往往比脸颊更暗。第二个特点比较了眼睛区域与鼻梁的强度。
1.引言
本文汇集了新的算法和见解，构筑一个鲁棒性良好的极速目标检测框架。这一框架主要是体现人脸检测的任务。为了实现这一目标，我们已经建立了一个正面的人脸检测系统，实现了相当于已公布的最佳结果的检测率和正误视率，[16，12，15，11，1]。这种人脸检测系统区分人脸比以往的方法都要清楚，而且速度很快。通过对384×288像素的图像，硬件环境是常规700 MHz英特尔奔腾III，人脸检测速度达到了每秒15帧。在其它人脸检测系统中，一些辅助信息如视频序列中的图像差异，或在彩色图像中像素的颜色，被用来实现高帧率。而我们的系统仅仅使用一个单一的灰度图像信息实现了高帧速率。上述可供选择的信息来源也可以与我们的系统集成，以获得更高的帧速率。

人脸识别对生活的影响英语作文

人脸识别对生活的影响英语作文The Impact of Face Recognition on Our Lives.Face recognition technology, often referred to asfacial recognition, is an advanced biometric technologythat identifies or verifies a person from their facial features. It has become a pivotal part of our modern-day lives, with applications ranging from smartphones to surveillance cameras and even law enforcement agencies. The widespread adoption of this technology has brought about significant changes in our day-to-day lives, bothpositively and negatively.On the positive side, face recognition has made our lives safer and more convenient. In the realm of security, it has enabled quick and accurate identification of individuals, particularly in crowded places like airports, stadiums, and concerts. This technology has also been used to apprehend fugitives and criminal suspects, often leading to the successful closure of long-standing cases.Furthermore, face recognition has found its way into our smartphones, enabling quick unlocking of devices and authentication for various apps and services.In addition to security, face recognition has also found applications in healthcare. It has been used to identify patients with dementia or Alzheimer's disease, who might have difficulty remembering their names or other identifying information. By using face recognition, healthcare professionals can ensure that the right patient receives the right treatment. Similarly, in the field of research, face recognition has been used to study and understand human emotions and facial expressions.However, despite its numerous benefits, face recognition technology also raises concerns about privacy and security. The biggest concern is the potential misuse of this technology. With the ability to identify and track individuals without their knowledge or consent, there is a risk of abuse by governments or private entities. For instance, there have been cases where governments have used face recognition technology to suppress dissent or monitorpolitical opponents. Similarly, private companies might use this technology to track customers' movements or preferences for marketing purposes.Moreover, the accuracy of face recognition technologyis not perfect. False positives and negatives can lead to misidentification, which can have serious consequences. For example, an innocent person might be wrongly identified as a criminal suspect or a fugitive, leading to unnecessary stress and even legal issues. Similarly, false negatives can result in the failure to identify a criminal or a fugitive, compromising public safety.Another concern is the potential for facial data to be stolen or misused. With the increasing number of devices and applications using face recognition, there is a growing risk of data breaches. If facial data is stolen, it can be used to spoof individuals' identities or to commit fraud. The potential for abuse is even higher in a world where facial data is collected and stored by multiple entities, including governments, private companies, and even hackers.Overall, face recognition technology has brought about significant changes in our lives, both positively and negatively. It has made our lives safer and more convenient by enabling quick and accurate identification ofindividuals in various contexts. However, it has also raised concerns about privacy, security, and accuracy. To ensure that the benefits of face recognition outweigh its risks, it is crucial that we carefully consider the ethical and social implications of this technology and ensure that it is used responsibly and transparently.。

人脸识别技术外文翻译文献编辑

人脸识别在中国的应用英语作文

人脸识别在中国的应用英语作文The rapid advancements in technology have transformed various aspects of our daily lives and one of the most prominent applications is in the field of facial recognition. China, known for its technological prowess, has been at the forefront of implementing facial recognition systems across a wide range of sectors. From public security to commercial applications, the integration of this innovative technology has significantly impacted the lives of the Chinese population.One of the primary areas where facial recognition has found extensive use in China is in the realm of public security. The Chinese government has invested heavily in the development and deployment of extensive surveillance networks utilizing facial recognition technology. These systems are strategically placed in public spaces such as transportation hubs, shopping malls, and residential areas to aid in the identification and tracking of individuals. The goal is to enhance public safety and combat criminal activities by providing law enforcement agencies with a powerful tool to quickly identify and apprehend suspects.The implementation of facial recognition in China's public security sector has been met with both praise and criticism. Proponents argue that the technology has proven effective in deterring and solving crimes, leading to a safer environment for citizens. They cite examples of successful cases where facial recognition has helped locate missing persons, identify perpetrators of various offenses, and even prevent terrorist attacks. However, critics raise concerns about the potential infringement of individual privacy and the creation of a surveillance state, where the government can closely monitor the movements and activities of its citizens without their consent.Beyond the realm of public security, facial recognition technology has also found widespread application in the commercial sector in China. Retailers have embraced this technology to enhance the customer experience and improve operational efficiency. Facial recognition systems are used to identify and track customer behavior within stores, allowing for personalized recommendations, targeted marketing, and streamlined checkout processes. Additionally, the technology has been integrated into various payment systems, enabling customers to make purchases simply by using their faces as a form of identification, eliminating the need for cash or cards.The integration of facial recognition in the commercial sector has been largely welcomed by Chinese consumers, who have embracedthe convenience and efficiency it offers. However, some individuals have raised concerns about the potential misuse of their personal data and the lack of transparency regarding the collection and storage of such information.Another notable application of facial recognition in China is in the realm of social services. The government has implemented facial recognition systems to streamline various administrative processes, such as accessing healthcare services, applying for government benefits, and verifying identities for various transactions. This integration has aimed to enhance the efficiency and accessibility of these services, particularly for the elderly and individuals living in remote areas who may have limited access to traditional identification documents.While the implementation of facial recognition in social services has been praised for its ability to improve the lives of Chinese citizens, there are concerns about the potential for exclusion and the risk of data breaches that could compromise sensitive personal information.The adoption of facial recognition technology in China has also extended to the education sector. Schools and universities have implemented systems to track student attendance, monitor classroom behavior, and even identify individuals who may pose a threat to campus safety. This integration has been touted as a meansof enhancing academic performance and ensuring the well-being of students, but it has also raised concerns about the potential infringement of student privacy and the creation of a culture of constant surveillance.Furthermore, the use of facial recognition technology has found its way into the realm of transportation in China. Airports, train stations, and other transportation hubs have incorporated these systems to streamline security checks, identify individuals on watchlists, and improve overall efficiency in passenger movement. While this integration has been praised for its ability to enhance travel experiences, it has also raised concerns about the potential for data breaches and the centralization of personal information.The widespread adoption of facial recognition technology in China has not been without its challenges. Concerns have been raised about the potential for bias and discrimination within these systems, as well as the lack of robust data privacy regulations to protect the personal information of citizens. There have been instances where the technology has been shown to be less accurate in identifying individuals with certain ethnic or gender backgrounds, raising questions about the fairness and inclusivity of these systems.Despite these challenges, the Chinese government has remained committed to the continued development and deployment of facialrecognition technology across various sectors. The potential benefits of this technology, such as enhanced public safety, improved service delivery, and increased operational efficiency, have been the driving force behind its widespread adoption.However, as the use of facial recognition continues to expand in China, it is crucial that policymakers, technology companies, and the public engage in constructive dialogues to address the ethical and privacy concerns surrounding this technology. Striking a balance between the benefits of facial recognition and the protection of individual rights will be essential in ensuring that the implementation of this technology aligns with the values of a just and equitable society.In conclusion, the application of facial recognition technology in China has been extensive and multifaceted, spanning sectors such as public security, commerce, social services, education, and transportation. While the technology has brought about significant improvements in various aspects of life, it has also raised concerns about privacy, bias, and the potential for misuse. As China continues to embrace this transformative technology, it is imperative that the country addresses these challenges and ensures that the implementation of facial recognition aligns with the principles of ethical and responsible technological development.。

外文文献翻译成品：基于人脸识别的移动自动课堂考勤管理系统(中英文双语对照)

外文标题：Face Recognition-Based Mobile Automatic Classroom Attendance Management System外文作者：Refik Samet,Muhammed Tanriverdi文献出处: 2018 International Conference on Cyberworlds (如觉得年份太老，可改为近2年，毕竟很多毕业生都这样做)英文2937单词，20013字符(字符就是印刷符)，中文4819汉字。

Face Recognition-Based Mobile Automatic ClassroomAttendance Management System Abstract—Classroom attendance check is a contributing factor to student participation and the final success in the courses. Taking attendance by calling out names or passing around an attendance sheet are both time-consuming, and especially the latter is open to easy fraud. As an alternative, RFID, wireless, fingerprint, and iris and face recognition-based methods have been tested and developed for this purpose. Although these methods have some pros, high system installation costs are the main disadvantage. The present paper aims to propose a face recognition-based mobile automatic classroom attendance management system needing no extra equipment. To this end, a filtering system based on Euclidean distances calculated by three face recognition techniques, namely Eigenfaces, Fisherfaces and Local Binary Pattern, has been developed for face recognition. The proposed system includes three different mobile applications for teachers, students, and parents to be installed on their smart phones to manage and perform the real-time attendance-taking process. The proposed system was tested among students at Ankara University, and the results obtained were very satisfactory.Keywords—face detection, face recognition, eigenfaces, fisherfaces, local binary pattern, attendance management system, mobile application, accuracyI.INTRODUCTIONMost educational institutions are concerned with st udents’ participation in courses since student participation in the classroom leads to effective learning and increases success rates [1]. Also, a high participation rate in the classroom is a motivating factor for teachers and contributes to a suitable environment for more willing and informative teaching [2]. The most common practice known to increase attendance in a course is taking attendance regularly. There are two common ways to create attendance data. Some teachers prefer to call names and put marks for absence or presence. Other teachers prefer to pass around a paper signing sheet. After gathering the attendance data via either of these two methods, teachers manually enter the data into the existing system. However, those non-technological methods are not efficient ways since they are time- consuming and prone to mistakes/fraud. The present paper aims to propose an attendance-taking process via the existing technological infrastructure with some improvements. A face recognition-based mobile automatic classroom attendance management system has been proposed with a face recognition infrastructure allowing the use of smart mobile devices. In this scope, a filtering system based on Euclidean distances calculated by three face recognition techniques, namely Eigenfaces, Fisherfaces, and Local Binary Pattern (LBP), has been developedfor face recognition. The proposed system includes three different applications for teachers, students, and parents to be installed on their smart phones to manage and perform a real-time polling process, data tracking, and reporting. The data is stored in a cloud server and accessible from everywhere at any time. Web services are a popular way of communication for online systems, and RESTful is an optimal example of web services for mobile online systems [3]. In the proposed system, RESTful web services were used for communication among teacher, student, and parent applications and the cloud server. Attendance results are stored in a database and accessible by the teacher, student and parent mobile applications.The paper is organised as follows. Section II provides a brief literature survey. SectionIII introduces the proposed system, and section IV follows by implementation and results. The last section gives the main conclusions.II.LITERATURE SURVEYFingerprint reading systems have high installation costs. Furthermore, only one student at a time can use a portable finger recognition device, which makes it atime-consuming process [4]. In the case of a fixed finger recognition device at the entrance of the classroom, attendance-taking should be done under the teacher's supervision so that students do not leave after the finger recognition, which makes the process time-consuming for both the teacher and the students. In case of RFID card reading systems, attendance-taking is available via the cards distributed to students [5]. In such systems, students may resort to fraudulent methods by reading their friends' cards. Also, if a student forgets his/her card, a non- true absence may be saved in the system. The disadvantage of the classroom scanning systems with Bluetooth or beacon methods is that each student must carry a device. Because the field limit of the Bluetooth Low Energy (BLE) system cannot be determined, students who are not inthe classroom at the moment but are within the Bluetooth area limits may appear to be present in the attendance system [6]. There are different methods of classroom attendance monitoring using face recognition technology. One of these is a camera placed at the classroom entrance and the students entering the classroom are registered into the system by face recognition [7]. However, in this system students’faces could be recognised, although students can leave the classroom afterwards, and errors can occur in the polling information. Another method is the observation carried out with a camera placed in the classroom and the classroom image taken during the course. In this case, the cameras used in the system need to be changed frequently to keep producing better quality images. Therefore, this system is not very useful andcan become costly. In addition to all the aforementioned disadvantages, the most common disadvantage is that all these methods need extra equipment. The proposed system has been developed to address these disadvantages. The main advantages of the proposed system are flexible usage, no equipment costs, no wasted time, and easy accessibility.III.PROPOSED SYSTEMA.Architecture of the Proposed SystemThe proposed system's architecture based on mobility and flexibility is shown inFig.1.Figure 1. System ArchitectureThe system consists of three layers: Application Layer, Communication Layer, and Server Layer.Application Layer: In the application layer, there are three mobile applications connected to the cloud server by web services. a) Teacher Application: The teacher is the head of the system, so he/she has the privilege to access all the data. By his/her smart mobile device, he/she can take a photo of students in a classroom at any time. After the taking the photograph, the teacher can use this photo to register attendance. For this aim, the photo is sent to the cloud server for face detection and recognition processing. The results are saved into a database together with all the reachable data. The teacher gets a response by the mobile application and can immediately see the results. The teacher can also create a student profile, add a photo of each student, and add or remove a student to/from their class rosters. He/she can as well create and delete courses. Each course has a unique six- character code. The teacher can share this code with his/her students so they can access their attendance results via the student application. The teacher can access to all data and results based on each student's recognized photo stamped with a date. Additionally, an email message with attendance data of a class in Excel format can be requested, while the analytics of the attendance results is provided in the application. b) Student Application: Students can sign in courses with the teacher's email address and the six-character course code. They can add their photos by taking a photo or a 3-second long video. In case of errors, their uploaded photos can be deleted. Students can only see limited results of the attendance-taking process related to their attendance. To protect personal privacy, the class photos and detected portrait photos of each student can be accessed only by the teacher. If students are not in the classroom when an attendance-check is performed, they are notified of the attendance-check. In case of errors (if a student is present, but not detected by the system), he/she can notify the teacher so he/she can fix the problem. c) Family Application: Parents can see their children's attendanceresults for each class. Additional children profiles can be added into the system. Each parent is added to the student's application with name, surname, and email address. When a student adds his/her parents, they are automatically able to see the attendance results. They are also notified when their child is not in the classroom.2) Communication Layer: RESTful web services are used to communicate betweenthe applications and server layers. Requests are sent by the POST method. Each request is sent with a unique ID of the authorised user of the session. Only the authorised users can access and respond the the data to which they have right to access. Due to its flexibility and fast performance, JSON is used as the data format for web services response [8]. With this abstract web service layer, the system can easily be used for a new item in the application layer, such as web pages or a new mobile operating system.3)Server Layer: The server layer is responsible for handling the requests and sending the results to the client. Face detection and recognition algorithms are performed in this layer and more than 30 different web services are created for handling different requests from mobile applications.B.Face DetectionAccurate and efficient face detection algorithms improve the accuracy level of theface recognition systems. If a face is not detected correctly, the system will fail its operation, stop processing, and restart. Knowledge-based, feature-based,template-based, and statistics-based methods are used for face detection [9]. Since the classroom photo is taken under the teacher's control, pose variations could be limited to a small range. Viola-Jones face detection method with Ada- boost training is shown as the best choice for real-time class attendance systems [9, 10]. In the most basic sense, the desired objects are firstly found and introduced according to a certain algorithm. Afterwards, they are scanned to find matches with similar shapes [11].C.Face RecognitionThere are two basic classifications of face recognition based on image intensity: feature-based and appearance-based [12]. Feature-based approaches try to represent (approximate) the object as compilations of different features, for example, eyes, nose, chin, etc. In contrast, the appearance-based models only use the appearance captured by different two-dimensional views of the object-of-interest. Feature-based techniques are more time-consuming than appearance-based techniques. The real-time attendance management system requires low computational process time. Therefore, three appearance-based face recognition techniques such as Eigenfaces, Fisherfaces and LBP are used in the tested system. Fisherfaces and eigenfaces techniques have a varying success rate, depending on different challenges, like pose variation, illumination, or facial expression [13]. According to several previous studies, face recognition using LBP method gives very good results regarding speed and discrimination performance as well as in different lighting conditions [14, 15]. Euclidean distance is calculated by finding similarities between images for face recognition. A filtering system based on Euclidean distances calculated by Eigenfaces, Fisherfaces and LBP has been developed for face recognition. According to the developed system, firstly, minimum Euclidean distances of LBP, Fisherfaces andEigenfaces algorithms are evaluated in defined order. If the Euclidean distance of LBP algorithm is less than 40; else if Euclidean distance of Fisherfaces algorithm is less than 250; else if Euclidean distance of Eigenfaces algorithm is less than 1500, recognized face is recorded as the right match. Secondly, if the calculated Euclidean distances by the three methods are greater than the minimum Euclidean distances, the second level Euclidean distances (40-50 (for LBP), 250-400 (for Fisherfaces), 1500- 1800 (for Eigenfaces)) are evaluated in the same way. If the second level conditions are also not met, the filter returns the wrong match. Thirdly, if any two algorithms give the same match result, the match is recorded correctly. Finally, if no conditions are met, the priority is given to the LBP algorithm and the match is recorded correctly. The system’s specific architecture aimed for flexibility, mobility, and low-cost by requiring no extra equipment. At the same time, its objective was to provide access to all users at any time. The system thus offers a real-time attendance management system to all its users.IV.IMPLEMENTATION AND RESULTSThe following platform was used. The cloud server has a 2.5 GHz with 4-core CPU,8GB RAM, and 64-bit operating system capacity. Viola-Jones face detection algorithm and Eigenfaces, Fisherfaces and LBP face recognition algorithms were implemented based on OpenCV. Tests were done with both iOS and ANDROID.Forty different attendance monitoring tests were performed in a real classroom, including 11 students, and 264 students’ faces were detected. Tables I, II, and III show detection and recognition accuracy of all three different types of tested algorithms related to the Euclidean distance.Priority ordering for 3 algorithms was arranged according to accuracy rate for each interval. In test results, 123, 89, and 85 false recognitions were detected for Eigenfaces, Fisherfaces and LBP, respectively. By the help of the developed filtering system, the number of false recognitions decreased to 65. Out of 40 implemented attendance monitoring tests, 10 were conducted with 1 face photo of each student in database in Step-I, 20 were conducted when the number of face photos increased up to 3 in Step-II, and 10 recognition processes were conducted with more than 3 face photos in database in Step-III. Table IV shows the obtained results.The most important limitation of tested attendance monitoring process is decreased success with increasing distance between the camera and students. The results regarding students sitting in front seats are more accurate in comparison to results regarding students sitting in the back. Secondly, the accuracy rates may have decreased due to the blurring caused by vibration while the photo was taken. Thirdly, in some cases one part of the student's face may be covered by another student sitting in front of him/her, which may hamper a successful face recognition process. Since the classroom photos are taken in uncontrolled environments, the illumination and pose could, to a large extent, affect the accuracy rate. The developed filtering system minimizes these effects. To increase accuracy, pose tolerant face recognition approach may also be used [16, 17].V.CONCLUSIONSThe present paper proposes a flexible and real-time face recognition-based mobile attendance management system. A filtering system based on Euclidean distances calculated by Eigenfaces, Fisherfaces, and LBP has been developed. The proposed system eliminates the cost for extra equipment, minimizes attendance-taking time, and allows users to access the data anytime and anywhere. Smart devices are very user- friendly to perform classroom attendance monitoring. Teachers, students, and parents can use the application without any restrictions and in real-time. Since the internet connection speed has been steadily increasing, high quality, larger images can be sent to the server. In addition, processor capacity of the servers is also increasing on daily basis. With these technological developments, the accuracy rate of the proposed system will also be increased. Face recognition could be further tested by other face recognition techniques, such as Support Vector Machine, Hidden Markov Model, Neural Networks, etc. Additionally, detection and recognition processes could be performed on smart devices once their processor capacity is sufficiently increased. REFERENCES[1]L. Stanca, "The Effects of Attendance on Academic Performance:Panel Data Evidence for Introductory Microeconomics," J. Econ. Educ., vol. 37, no. 3, pp. 251–266, 2006.[2]P.K. Pani and P. Kishore, "Absenteeism and performance in a quantitative moduleA quantile regression analysis," Journal of Applied Research in Higher Education, vol.8 no. 3, pp. 376-389, 2016.[3]U. Thakar, A. Tiwari, and S. Varma, "On Composition of SOAP Based and RESTful Services," IEEE 6th Int. Conference on Advanced Computing (IACC), 2016. [4]K.P.M. Basheer and C.V. Raghu, "Fingerprint attendance system for classroom needs," Annual IEEE India Conference (INDICON), pp. 433-438, 2012.[5]S. Konatham, B.S. Chalasani, N. Kulkarni, and T.E. Taeib, ―Attendance generating system using RFID and GSM,‖IEEE Long Island Systems, Applications and Technology Conference (LISAT), 2016.[6]S. Noguchi, M. Niibori, E. Zhou, and M. Kamada, "Student Attendance Management System with Bluetooth Low Energy Beacon and Android Devices," 18th International Conference on Network- Based Information Systems, pp. 710-713, 2015.[7]S. Chintalapati and M.V. Raghunadh, ―Automated attendance management system based on face recognition algorithms,‖IEEE Int. Conference on Computational Intelligence and Computing Research, 2013.[8]G. Wang, "Improving Data Transmission in Web Applications via the Translation between XML and JSON," Third Int. Conference on Communications and Mobile Computing (CMC), pp. 182-185, 2011.[9]X. Zhu, D. Ren, Z. Jing, L. Yan, and S. Lei, "Comparative Research of theCommon Face Detection Methods," 2nd International Conference on Computer Science and Network Technology, pp. 1528-1533, 2012.[10]V. Gupta and D. Sharma, ―A Study of Various Face Detection Methods,‖International Journal of Advanced Research in Computer and Communication Engineering vol. 3, no. 5, pp.6694-6697, 2014.[11]P. Viaola and M.J. Jones, ―Robust Real-Time Face Detection,‖International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.[12]L. Masupha, T. Zuva, S. Ngwira, and O. Esan, ―Face recognition techniques, their advantages, disadvantages and performance evaluation,‖Int. Conference on Computing, Communication and Security (ICCCS), 2015.[13]J. Li, S. Zhou, and C. Shekhar, "A comparison of subspace analysis for face recognition," International Conference on Multimedia and Expo, ICME '03, Proceedings, vol. 3, pp. 121-124, 2003.[14]T. Ahonen, A. Hadid, and M. Pietikainen, ―Face description with Local Binary Patterns,‖IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, 2006.[15]T. Ahonen, A. Hadid, M. Pietikainen, and T . Maenpaa, ―Face recognition based on the appearance of local regions,‖Proceedings of the 17th Int. Conference on Pattern Recognition, vol. 3, pp. 153-156, 2004.[16]R. Samet, S. Sakhi, and K. B. Baskurt, ―An Efficient Pose Tolerant Face Recognition Approach‖, Transactions on Comput. Science XXVI, LNCS 9550, pp.161-172, 2016.[17]R. Samet, G. S. Shokouh, J. Li, ―A Novel Pose Tolerant Face Recognition Approach‖, 2014 International Conference on Cyberworlds, pp. 308-312, 2014.基于人脸识别的移动自动课堂考勤管理系统摘要- 课堂出勤检查是学生参与和课程最终成功的一个因素。

1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。

人脸识别论文中英文附录(原文及译文)翻译原文来自Thomas David Heseltine BSc. Hons. The University of YorkDepartment of Computer ScienceFor the Qualification of PhD. -- September 2005 -《Face Recognition: Two-Dimensional and Three-Dimensional Techniques》4 Two-dimensional Face Recognition4.1 Feature LocalizationBefore discussing the methods of comparing two facial images we now take a brief look at some at the preliminary processes of facial feature alignment. This process typically consists of two stages: face detection and eye localisation. Depending on the application, if the position of the face within the image is known beforehand (for a cooperative subject in a door access system for example) then the face detection stage can often be skipped, as the region of interest is already known. Therefore, we discuss eye localisation here, with a brief discussion of face detection in the literature review(section 3.1.1).The eye localisation method is used to align the 2D face images of the various test sets used throughout this section. However, to ensure that all results presented arerepresentative of the face recognition accuracy and not a product of the performance of the eye localisation routine, all image alignments are manually checked and any errors corrected, prior to testing and evaluation.We detect the position of the eyes within an image using a simple template based method. A training set of manually pre-aligned images of faces is taken, and eachimage cropped to an area around both eyes. The average image is calculated and usedas a template.Figure 4-1 - The average eyes. Used as a template for eye detection.Both eyes are included in a single template, rather than individually searching for each eye in turn, as the characteristic symmetry of the eyes either side of the nose, provides a useful feature that helps distinguish between the eyes and other false positives that may be picked up in the background. Although this method is highly susceptible to scale(i.e. subject distance from thecamera) and also introduces the assumption that eyes in the image appear near horizontal. Some preliminary experimentation also reveals that it is advantageous to include the area of skin just beneath the eyes. The reason being that in some cases the eyebrows can closely match the template, particularly if there are shadows in the eye-sockets, but the area of skin below the eyes helps to distinguish the eyes from eyebrows (the area just below the eyebrows contain eyes, whereas the area below the eyes contains only plain skin).A window is passed over the test images and the absolute difference taken to that of the average eye image shown above. The area of the image with the lowest difference is taken as the region of interest containing the eyes. Applying the same procedure using a smaller template of the individual left and right eyes then refines each eye position.This basic template-based method of eye localisation, although providing fairly preciselocalisations, often fails to locate the eyes completely. However, we are able to improve performance by including a weighting scheme.Eye localisation is performed on the set of training images, which is then separated into two sets: those in which eye detection was successful; and those in which eye detection failed. Taking the set of successful localisations we compute the average distance from the eye template (Figure 4-2 top). Note that the image is quite dark, indicating that the detected eyes correlate closely to the eye template, as we would expect. However, bright points do occur near the whites of the eye, suggesting that this area is often inconsistent, varying greatly from the average eye template.Figure 4-2 – Distance to the eye template for successful detections (top) indicating variance due tonoise and failed detections (bottom) showing credible variance due to miss-detected features.In the lower image (Figure 4-2 bottom), we have taken the set of failed localisations(images of the forehead, nose, cheeks, background etc. falsely detected by the localisation routine) and once again computed the average distance from the eye template. The bright pupils surrounded by darker areas indicate that a failed match is often due to the high correlation of the nose and cheekbone regions overwhelming the poorly correlated pupils. Wanting to emphasise thedifference of the pupil regions for these failed matches and minimise the variance of the whites of the eyes for successful matches, we divide the lower image values by the upper image to produce a weights vector as shown in Figure 4-3. When applied to the difference image before summing a total error, this weighting scheme provides a much improved detection rate.Figure 4-3 - Eye template weights used to give higher priority to those pixels that best represent the eyes.4.2 The Direct Correlation ApproachWe begin our investigation into face recognition with perhaps the simplest approach,known as the direct correlation method (also referred to as template matching by Brunelli and Poggio [ 29 ]) involving the direct comparison of pixel intensity values taken from facial images. We use the term ‘Direct Correlation’ to encompass all techniques in which face images are compared directly, without any form of image space analysis, weighting schemes or feature extraction, regardless of the di stance metric used. Therefore, we do not infer that Pearson’s correlation is applied as the similarity function (although such an approach would obviously come under our definition of direct correlation). We typically use the Euclidean distance as our metric in these investigations (inversely related to Pearson’s correlation and can be considered as a scale and translation sensitive form of image correlation), as this persists with the contrast made between image space and subspace approaches in later sections.Firstly, all facial images must be aligned such that the eye centres are located at two specified pixel coordinates and the image cropped to remove any backgroundinformation. These images are stored as greyscale bitmaps of 65 by 82 pixels and prior to recognition converted into a vector of 5330 elements (each element containing the corresponding pixel intensity value). Each corresponding vector can be thought of as describing a point within a 5330 dimensional image space. This simple principle can easily be extended to much larger images: a 256 by 256 pixel image occupies a single point in 65,536-dimensional image space and again, similar images occupy close points within that space. Likewise, similar faces are located close together within the image space, while dissimilar faces are spaced far apart. Calculating the Euclidean distance d, between two facial image vectors (often referred to as the query image q, and gallery image g), we get an indication of similarity. A threshold is then applied to make the final verification decision.d q g (d threshold ⇒accept ) (d threshold ⇒reject ) . Equ. 4-14.2.1 Verification TestsThe primary concern in any face recognition system is its ability to correctly verify a claimed identity or determine a person's most likely identity from a set of potential matches in a database. In order to assess a given system’s ability to perform these tasks, a variety of evaluation methodologies have arisen. Some of these analysis methods simulate a specific mode of operation (i.e. secure site access or surveillance), while others provide a more mathematical description of data distribution in someclassification space. In addition, the results generated from each analysis method maybe presented in a variety of formats. Throughout the experimentations in this thesis, we primarily use the verification test as our method of analysis and comparison, although we also use Fisher’s Linear Discriminant to analyse individual subspace components in section 7 and the identification test for the final evaluations described in section 8. The verification test measures a system’s ability to correctly accept or reject the proposed identity of an individual. At a functional level, this reduces to two images being presented for comparison, for which the system must return either an acceptance (the two images are of the same person) or rejection (the two images are of different people). The test is designed to simulate the application area of secure site access. In this scenario, a subject will present some form of identification at a point of entry, perhaps as a swipe card, proximity chip or PIN number. This number is then used to retrieve a stored image from a database of known subjects (often referred to as the target or gallery image) and compared with a live image captured at the point of entry (the query image). Access is then granted depending on the acceptance/rejection decision.The results of the test are calculated according to how many times the accept/reject decision is made correctly. In order to execute this test we must first define our test set of face images. Although the number of images in the test set does not affect the results produced (as the error rates are specified as percentages of image comparisons), it is important to ensure that the test set is sufficiently large such that statistical anomalies become insignificant (for example, a couple of badly aligned images matching well). Also, the type of images (high variation in lighting, partial occlusions etc.) will significantly alter the results of the test. Therefore, in order to compare multiple face recognition systems, they must be applied to the same test set.However, it should also be noted that if the results are to be representative of system performance in a real world situation, then the test data should be captured under precisely the same circumstances as in the application environment.On the other hand, if the purpose of the experimentation is to evaluate and improve a method of face recognition, which may be applied to a range of application environments, then the test data should present the range of difficulties that are to be overcome. This may mean including a greater percentage of ‘difficult’ images thanwould be expected in the perceived operating conditions and hence higher error rates in the results produced. Below we provide the algorithm for executing the verification test. The algorithm is applied to a single test set of face images, using a single function call to the face recognition algorithm: CompareFaces(FaceA, FaceB). This call is used to compare two facial images, returning a distance score indicating how dissimilar the two face images are: the lower the score the more similar the two face images. Ideally, images of the same face should produce low scores, while images of different faces should produce high scores.Every image is compared with every other image, no image is compared with itself and no pair is compared more than once (we assume that the relationship is symmetrical). Once two images have been compared, producing a similarity score, the ground-truth is used to determine if the images are of the same person or different people. In practical tests this information is often encapsulated as part of the image filename (by means of a unique person identifier). Scores are then stored in one of two lists: a list containing scores produced by comparing images of different people and a list containing scores produced by comparing images of the same person. The final acceptance/rejection decision is made by application of a threshold. Any incorrect decision is recorded as either a false acceptance or false rejection. The false rejection rate (FRR) is calculated as the percentage of scores from the same people that were classified as rejections. The false acceptance rate (FAR) is calculated as the percentage of scores from different people that were classified as acceptances.For IndexA = 0 to length(TestSet)For IndexB = IndexA+1 to length(TestSet)Score = CompareFaces(TestSet[IndexA], TestSet[IndexB])If IndexA and IndexB are the same personAppend Score to AcceptScoresListElseAppend Score to RejectScoresListFor Threshold = Minimum Score to Maximum Score:FalseAcceptCount, FalseRejectCount = 0For each Score in RejectScoresListIf Score <= ThresholdIncrease FalseAcceptCountFor each Score in AcceptScoresListIf Score > ThresholdIncrease FalseRejectCountFalseAcceptRate = FalseAcceptCount / Length(AcceptScoresList)FalseRejectRate = FalseRejectCount / length(RejectScoresList)Add plot to error curve at (FalseRejectRate, FalseAcceptRate)These two error rates express the inadequacies of the system when operating at aspecific threshold value. Ideally, both these figures should be zero, but in reality reducing either the FAR or FRR (by altering the threshold value) will inevitably resultin increasing the other. Therefore, in order to describe the full operating range of aparticular system, we vary the threshold value through the entire range of scoresproduced. The application of each threshold value produces an additional FAR, FRRpair, which when plotted on a graph produces the error rate curve shown below.Figure 4-5 - Example Error Rate Curve produced by the verification test.The equal error rate (EER) can be seen as the point at which FAR is equal to FRR. This EER value is often used as a single figure representing the general recognitionperformance of a biometric system and allows for easy visual comparison of multiple methods. However, it is important to note that the EER does not indicate the level oferror that would be expected in a real world application. It is unlikely that any realsystem would use a threshold value such that the percentage of false acceptances wereequal to the percentage of false rejections. Secure site access systems would typicallyset the threshold such that false acceptances were significantly lower than false rejections: unwilling to tolerate intruders at the cost of inconvenient access denials.Surveillance systems on the other hand would require low false rejection rates tosuccessfully identify people in a less controlled environment. Therefore we should bear in mind that a system with a lower EER might not necessarily be the better performer towards the extremes of its operating capability.There is a strong connection between the above graph and the receiver operating characteristic (ROC) curves, also used in such experiments. Both graphs are simply two visualisations of the same results, in that the ROC format uses the True Acceptance Rate(TAR), where TAR = 1.0 – FRR in place of the FRR, effectively flipping the graph vertically. Another visualisation of the verification test results is to display both the FRR and FAR as functions of the threshold value. This presentation format provides a reference to determine the threshold value necessary to achieve a specific FRR and FAR. The EER can be seen as the point where the two curves intersect.Figure 4-6 - Example error rate curve as a function of the score threshold The fluctuation of these error curves due to noise and other errors is dependant on the number of face image comparisons made to generate the data. A small dataset that only allows for a small number of comparisons will results in a jagged curve, in which large steps correspond to the influence of a single image on a high proportion of thecomparisons made. A typical dataset of 720 images (as used in section 4.2.2) provides258,840 verification operations, hence a drop of 1% EER represents an additional 2588 correct decisions, whereas the quality of a single image could cause the EER tofluctuate by up to 0.28.4.2.2 ResultsAs a simple experiment to test the direct correlation method, we apply the technique described above to a test set of 720 images of 60 different people, taken from the AR Face Database [ 39 ]. Every image is compared with every other image in the test set to produce a likeness score, providing 258,840 verification operations from which to calculate false acceptance rates and false rejection rates. The error curve produced is shown in Figure 4-7.Figure 4-7 - Error rate curve produced by the direct correlation method using no image preprocessing.We see that an EER of 25.1% is produced, meaning that at the EER thresholdapproximately one quarter of all verification operations carried out resulted in anincorrect classification. There are a number of well-known reasons for this poor levelof accuracy. Tiny changes in lighting, expression or head orientation cause the location in image space to change dramatically. Images in face space are moved far apart due to these image capture conditions, despite being of the same person’s face. The distance between images of different people becomes smaller than the area of face space covered by images of the same person and hence false acceptances and false rejections occur frequently. Other disadvantages include the large amount of storage necessary for holding many face images and the intensive processing required for each comparison, making this method unsuitable for applications applied to a large database. In section 4.3 we explore the eigenface method, which attempts to address some of these issues.4 二维人脸识别4.1 功能定位在讨论比较两个人脸图像，我们现在就简要介绍的方法一些在人脸特征的初步调整过程。