人脸识别Face detectionPPT课件
相关主题
- 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)。
• A megapixel image has ~106 pixels and a comparable number of candidate face locations
• To avoid having a false positive in every image image, our false positive rate has to be less than 10-6
MATLAB: ii = cumsum(cumsum(double(i)), 2);
Computing sum within a rectangle
• Let A,B,C,D be the
values of the integral
image at the corners of a
rectangle
Face detection
Many slides adapted from P. Viola
Face detection
• Basic idea: slide a window across image and evaluate a face model at every location
Challenges of face detection
• For a 24x24 detection region, the number of possible rectangle features is ~160,000!
• At test time, it is impractical to evaluate the entire feature set
P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR 2001. P. Viola and M. Jones. Robust real-time face detection. IJCV 57(2), 2004.
• A weak learner need only do better than chance
• Training consists of multiple boosting rounds
• Sliding window detector must evaluate tens of thousands of location/scale combinations
• Faces are rare: 0–10 per image
• For computational efficiency, we should try to spend as little time as possible on the non-face windows
D
B
• Then the sum of original
image values within the
rectangle can be
C
A
computed as:
sum = A – B – C + D
• Only 3 additions are required for any size of rectangle!
• Can we create a good classifier using just a small subset of all possible features?
• How to select such a subset?
Boosting
• Boosting is a classification swenku.baidu.comheme that works by combining weak learners into a more accurate ensemble classifier
The Viola/Jones Face Detector
• A seminal approach to real-time object detection
• Training is slow, but detection is very fast • Key ideas
• Integral images for fast feature evaluation • Boosting for feature selection • Attentional cascade for fast rejection of non-face windows
Example
Integral Image
-1
+1
+2
-2
-1
+1
Feature selection
• For a 24x24 detection region, the number of possible rectangle features is ~160,000!
Feature selection
Image Features
“Rectangle filters”
Value = ∑ (pixels in white area) – ∑ (pixels in black area)
Example
Source
Result
Fast computation with integral images
Computing the integral image
Computing the integral image
ii(x, y-1) s(x-1, y)
i(x, y)
Cumulative row sum: s(x, y) = s(x–1, y) + i(x, y) Integral image: ii(x, y) = ii(x, y−1) + s(x, y)
• The integral image computes a value at each
pixel (x,y) that is the sum
of the pixel values above and to the left of (x,y),
(x,y)
inclusive
• This can quickly be computed in one pass through the image
• To avoid having a false positive in every image image, our false positive rate has to be less than 10-6
MATLAB: ii = cumsum(cumsum(double(i)), 2);
Computing sum within a rectangle
• Let A,B,C,D be the
values of the integral
image at the corners of a
rectangle
Face detection
Many slides adapted from P. Viola
Face detection
• Basic idea: slide a window across image and evaluate a face model at every location
Challenges of face detection
• For a 24x24 detection region, the number of possible rectangle features is ~160,000!
• At test time, it is impractical to evaluate the entire feature set
P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. CVPR 2001. P. Viola and M. Jones. Robust real-time face detection. IJCV 57(2), 2004.
• A weak learner need only do better than chance
• Training consists of multiple boosting rounds
• Sliding window detector must evaluate tens of thousands of location/scale combinations
• Faces are rare: 0–10 per image
• For computational efficiency, we should try to spend as little time as possible on the non-face windows
D
B
• Then the sum of original
image values within the
rectangle can be
C
A
computed as:
sum = A – B – C + D
• Only 3 additions are required for any size of rectangle!
• Can we create a good classifier using just a small subset of all possible features?
• How to select such a subset?
Boosting
• Boosting is a classification swenku.baidu.comheme that works by combining weak learners into a more accurate ensemble classifier
The Viola/Jones Face Detector
• A seminal approach to real-time object detection
• Training is slow, but detection is very fast • Key ideas
• Integral images for fast feature evaluation • Boosting for feature selection • Attentional cascade for fast rejection of non-face windows
Example
Integral Image
-1
+1
+2
-2
-1
+1
Feature selection
• For a 24x24 detection region, the number of possible rectangle features is ~160,000!
Feature selection
Image Features
“Rectangle filters”
Value = ∑ (pixels in white area) – ∑ (pixels in black area)
Example
Source
Result
Fast computation with integral images
Computing the integral image
Computing the integral image
ii(x, y-1) s(x-1, y)
i(x, y)
Cumulative row sum: s(x, y) = s(x–1, y) + i(x, y) Integral image: ii(x, y) = ii(x, y−1) + s(x, y)
• The integral image computes a value at each
pixel (x,y) that is the sum
of the pixel values above and to the left of (x,y),
(x,y)
inclusive
• This can quickly be computed in one pass through the image