基于MATLAB的人脸识别源程序
基于matlab的人脸识别源代码
function varargout = FR_Processed_histogram(varargin) %这种算法是基于直方图处理的方法%The histogram of image is calculated and then bin formation is done on the%basis of mean of successive graylevels frequencies. The training is done on odd images of 40 subjects (200 images out of 400 images)%The results of the implemented algorithm is 99.75 (recognition fails on image number 4 of subject 17)gui_Singleton = 1;gui_State = struct('gui_Name', mfilename, ...'gui_Singleton', gui_Singleton, ...'gui_OpeningFcn', @FR_Processed_histogram_OpeningFcn.,..'gui_OutputFcn',@FR_Processed_histogram_OutputFcn.,..'gui_LayoutFcn', [] , ... 'gui_Callback', []);if nargin && ischar(varargin{1}) gui_State.gui_Callback =str2func(varargin{1});endif nargout[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});elsegui_mainfcn(gui_State, varargin{:});end% End initialization code - DO NOT EDIT% -------------------------------------------------------------------------% --- Executes just before FR_Processed_histogram is made visible. function FR_Processed_histogram_OpeningFcn(hObjecte, ventdata, handles, varargin)% This function has no output args, see OutputFcn.% hObject handle to figure% eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA) % varargin command line arguments to FR_Processed_histogram (see VARARGIN)% Choose default command line output forFR_Processed_histogramhandles.output = hObject;% Update handles structure guidata(hObject, handles);% UIWAIT makes FR_Processed_histogram wait for user response(see UIRESUME)% uiwait(handles.figure1);global total_sub train_img sub_img max_hist_level bin_numform_bin_num;total_sub = 40;train_img = 200;sub_img = 10;max_hist_level = 256;bin_num = 9;form_bin_num = 29;% -------------------------------------------------------------------------% --- Outputs from this function are returned to the command line.function varargout = FR_Processed_histogram_OutputFcn(hObject, eventdata, handles)% varargout cell array for returning output args (see VARARGOUT);% hObject handle to figure% eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA)% Get default command line output from handles structurevarargout{1} = handles.output;% -------------------------------------------------------------------------% --- Executes on button press in train_button.function train_button_Callback(hObject, eventdata, handles)% hObject handle to train_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA)global train_processed_bin;global total_sub train_img sub_img max_hist_level bin_numform_bin_num;train_processed_bin(form_bin_num,train_img) = 0;K = 1;train_hist_img = zeros(max_hist_level, train_img);for Z=1:1:total_subfor X=1:2:sub_img %%%train on odd number of images of each subjectI = imread( strcat('ORL\S',int2str(Z), '\',int2str(X), '.bmp') ); [rowscols] = size(I);for i=1:1:rowsfor j=1:1:colsif( I(i,j) == 0 ) train_hist_img(max_hist_level, K)train_hist_img(max_hist_level, K) + 1;else train_hist_img(I(i,j), K) = train_hist_img(I(i,j), K) + 1;endendendK = K + 1;endend[r c] = size(train_hist_img);sum = 0;for i=1:1:cK = 1;for j=1:1:rif( (mod(j,bin_num)) == 0 )sum = sum + train_hist_img(j,i);train_processed_bin(K,i) = sum/bin_num; K = K + 1;sum = 0;elsesum = sum + train_hist_img(j,i);endendtrain_processed_bin(K,i) = sum/bin_num;enddisplay ('Training Done') save'train' train_processed_bin;% --- Executes on button press in Testing_button.function Testing_button_Callback(hObject, eventdata, handles)% hObject handle to Testing_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA) global train_img max_hist_level bin_num form_bin_num;global train_processed_bin;global filename pathname Iload 'train'test_hist_img(max_hist_level) = 0;test_processed_bin(form_bin_num) = 0;[rows cols] = size(I);for i=1:1:rowsfor j=1:1:colsif( I(i,j) == 0 )test_hist_img(max_hist_level)test_hist_img(max_hist_level) + 1;elsetest_hist_img(I(i,j)) = test_hist_img(I(i,j)) + 1;endendend[r c] = size(test_hist_img); sum = 0;K = 1;for j=1:1:cif( (mod(j,bin_num)) == 0 )sum = sum + test_hist_img(j); test_processed_bin(K) =sum/bin_num;K = K + 1;sum = 0;elsesum = sum + test_hist_img(j);endendtest_processed_bin(K) = sum/bin_num;sum = 0;K = 1;for y=1:1:train_imgfor z=1:1:form_bin_numsum = sum + abs( test_processed_bin(z) - train_processed_bin(z,y) );endimg_bin_hist_sum(K,1) = sum;sum = 0;K = K + 1;end[temp M] = min(img_bin_hist_sum);M = ceil(M/5);getString_start=strfind(pathname',S');getString_start=getString_start(end)+1;getString_end=strfind(pathname',\');getString_end=getString_end(end)-1;subjectindex=str2num(pathname(getString_start:getString_end));if (subjectindex == M)axes (handles.axes3)%image no: 5 is shown for visualization purposeimshow(imread(STRCAT('ORL\S',num2str(M),'\5.bmp')))msgbox ( 'Correctly Recognized');elsedisplay ([ 'Error==> Testing Image of Subject >>'num2str(subjectindex) ' matches with the image of subject >> 'num2str(M)])axes (handles.axes3)%image no: 5 is shown for visualization purposeimshow(imread(STRCAT( 'ORL\S' ,num2str(M),'\5.bmp')))msgbox ( 'Incorrectly Recognized');enddisplay('Testing Done')% -------------------------------------------------------------------------function box_Callback(hObject, eventdata, handles)% hObject handle to box (see GCBO)% eventdata reserved - to be defined in a future version ofMATLAB% handles structure with handles and user data (see GUIDATA)% Hints: get(hObject,'String') returns contents of box as text% str2double(get(hObject,'String')) returns contents of box as a double% -------------------------------------------------------------------------% --- Executes during object creation, after setting all properties.function box_CreateFcn(hObject, eventdata, handles)% hObject handle to box (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB % handles empty - handles not created until after all CreateFcns called% Hint: edit controls usually have a white background on Windows.% See ISPC and COMPUTER.if ispc && isequal(get(hObject,'BackgroundColor'),get(0,'defaultUicontrolBackgroundColor'))set(hObject,'BackgroundColor','white');end% --- Executes on button press in Input_Image_button.function Input_Image_button_Callback(hObject, eventdata, handles) % hObject handle to Input_Image_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB % handles structure with handles and user data (see GUIDATA) global filename pathname I[filename, pathname] = uigetfile('*.bmp', 'Test Image');axes(handles.axes1)imgpath=STRCAT(pathname,filename);I = imread(imgpath);imshow(I)% -------------------------------------------------------------------------% --- Executes during object creation, after setting all properties.function axes3_CreateFcn(hObject, eventdata, handles)% hObject handle to axes3 (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles empty - handles not created until after all CreateFcns called% Hint: place code in OpeningFcn to populate axes3%Programmed by Usman Qayyum。
基于matlab程序实现人脸识别
基于matlab程序实现人脸识别
人脸识别已经成为一个广泛被应用的技术,例如手机的解锁方式,安全系统等等。
它是一种基于人脸图像进行身份验证或身份识别的技术,也是近年来计算机视觉和模式识别领域研究的热点方向之一。
在这篇文档中,我们将介绍如何使用matlab编写一个简单的人脸识别程序。
人脸识别是什么?
人脸识别可以被定义为一个过程,旨在使用数字算法识别和验证图像或视频中
人脸身份。
在计算机科学的领域中,这项技术可以被描述为一种模式识别技术,
旨在通过在人脸图像上提取可识别特征来确定身份验证。
通俗易懂地理解,就是计算机能够识别人脸的特征,并将其与已知的数据匹配,从而确定人物身份。
人脸识别程序的开发流程
以下是本文介绍的基本程序开发流程:
1.数据集导入和预处理
2.特征提取和脸部对齐
3.模型训练和分类器设计
4.模型评估和测试
数据集导入和预处理
考虑到一个好的项目,我们需要一个良好的数据集。
在这里,我们可以使用来
自orl人脸数据集的数据。
该数据集中包含的有40个人的400幅灰度图像,每个
人有10个不同的示例。
您可以从该网站下载并使用这些数据来测试您的算法。
在这个过程中,我们需要使用matlab中的imread函数将数据读取为数字矩阵,然后将数据分为训练集和测试集。
这个过程旨在将原始的数据转换为我们算法能
够处理的数字矩阵,并将数据划分为训练集和测试集。
``` % 读取数据集 dataFolderPath =。
基于matlab的人脸检测程序
基于Matlab的一个最简单的人脸检测程序2010-08-09 20:28:39| 分类:默认分类| 标签:matlab 人脸检测程序|字号大中小订阅clear;I=imread('E:\Matlab\图片\q5.jpg');O=rgb2ntsc(I);G=O(:,:,2);[m n]=size(G);U=zeros(m,n);for i=1:mfor j=1:nif G(i,j)>0.03&&G(i,j)<0.16U(i,j)=1;endendendsr=strel('disk',6);C=imclose(U,sr);L=bwlabel(C);B=regionprops(L,'area');Se=[B.Area];Sm=max(Se);if Sm>m*n/27B1=bwareaopen(C,Sm);k_y1=m;k2=m;l2=n;if any(B1(i,:))==1k_y1=i;breakendendfor i=k_y1:mif B1(i,:)==0k2=i;breakendendfor j=1:nif any(B1(:,j))==1l_y1=j;breakendendfor j=l_y1:nif B1(:,j)==0l2=j;breakendendk_y=k2-k_y1;if k_y>.5*l&&k_y<3*lI1=imcrop(B1,[l_y1 k_y1 l .4*k_y]); [n1 m1]=size(I1);L1=bwlabel(I1);E=regionprops(L1,'area');Si=[E.Area];Sm=max(Si);if Sm/(n1*m1)>.3B2=bwareaopen(I1,floor(.5*Sm)); g_y1=m1;g2=m1;for j=1:m1if any(B2(:,j))==1g_y1=j;breakendendfor j=g_y1:m1if B2(:,j)==0;g2=j;breakendendg=g2-g_y1;figure;imshow(I);hold onh1=line([l_y1+g_y1,l_y1+g_y1+g],[k_y1,k_y1]);h2=line([l_y1+g_y1+g,l_y1+g_y1+g],[k_y1,k_y1+1.1*g]);h3=line([l_y1+g_y1+g,l_y1+g_y1],[k_y1+1.1*g,k_y1+1.1*g]);h4=line([l_y1+g_y1,l_y1+g_y1],[k_y1+1.1*g,k_y1]);h=[h1 h2 h3 h4];set(h,'Color',[1 0 0],'LineWidth',2);elsefigure;imshow(I);endelsefigure;imshow(I);endelsefigure;imshow(I);end注:本程序是基于肤色的人脸侦测程序,较为简单,只能检测出一个人脸,对于背景较单调的情况下的个体照,有较高的检测率,而且检测速度快。
(完整版)人脸识别MATLAB代码
1.色彩空间转换function [r,g]=rgb_RGB(Ori_Face)R=Ori_Face(:,:,1);G=Ori_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8型转换成double型G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;row=size(Ori_Face,1); % 行像素column=size(Ori_Face,2); % 列像素for i=1:rowfor j=1:columnrr(i,j)=R1(i,j)/RGB(i,j);gg(i,j)=G1(i,j)/RGB(i,j);endendrrr=mean(rr);r=mean(rrr);ggg=mean(gg);g=mean(ggg);2.均值和协方差t1=imread('D:\matlab\皮肤库\1.jpg');[r1,g1]=rgb_RGB(t1); t2=imread('D:\matlab\皮肤库\2.jpg');[r2,g2]=rgb_RGB(t2); t3=imread('D:\matlab\皮肤库\3.jpg');[r3,g3]=rgb_RGB(t3); t4=imread('D:\matlab\皮肤库\4.jpg');[r4,g4]=rgb_RGB(t4); t5=imread('D:\matlab\皮肤库\5.jpg');[r5,g5]=rgb_RGB(t5); t6=imread('D:\matlab\皮肤库\6.jpg');[r6,g6]=rgb_RGB(t6); t7=imread('D:\matlab\皮肤库\7.jpg');[r7,g7]=rgb_RGB(t7); t8=imread('D:\matlab\皮肤库\8.jpg');[r8,g8]=rgb_RGB(t8);t9=imread('D:\matlab\皮肤库\9.jpg');[r9,g9]=rgb_RGB(t9);t10=imread('D:\matlab\皮肤库\10.jpg');[r10,g10]=rgb_RGB(t10);t11=imread('D:\matlab\皮肤库\11.jpg');[r11,g11]=rgb_RGB(t11);t12=imread('D:\matlab\皮肤库\12.jpg');[r12,g12]=rgb_RGB(t12);t13=imread('D:\matlab\皮肤库\13.jpg');[r13,g13]=rgb_RGB(t13);t14=imread('D:\matlab\皮肤库\14.jpg');[r14,g14]=rgb_RGB(t14);t15=imread('D:\matlab\皮肤库\15.jpg');[r15,g15]=rgb_RGB(t15);t16=imread('D:\matlab\皮肤库\16.jpg');[r16,g16]=rgb_RGB(t16);t17=imread('D:\matlab\皮肤库\17.jpg');[r17,g17]=rgb_RGB(t17);t18=imread('D:\matlab\皮肤库\18.jpg');[r18,g18]=rgb_RGB(t18);t19=imread('D:\matlab\皮肤库\19.jpg');[r19,g19]=rgb_RGB(t19);t20=imread('D:\matlab\皮肤库\20.jpg');[r20,g20]=rgb_RGB(t20);t21=imread('D:\matlab\皮肤库\21.jpg');[r21,g21]=rgb_RGB(t21);t22=imread('D:\matlab\皮肤库\22.jpg');[r22,g22]=rgb_RGB(t22);t23=imread('D:\matlab\皮肤库\23.jpg');[r23,g23]=rgb_RGB(t23);t24=imread('D:\matlab\皮肤库\24.jpg');[r24,g24]=rgb_RGB(t24);t25=imread('D:\matlab\皮肤库\25.jpg');[r25,g25]=rgb_RGB(t25);t26=imread('D:\matlab\皮肤库\26.jpg');[r26,g26]=rgb_RGB(t26);t27=imread('D:\matlab\皮肤库\27.jpg');[r27,g27]=rgb_RGB(t27);r=cat(1,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,r13,r14,r15,r16,r17,r18,r19,r20,r21,r22, r23,r24,r25,r26,r27);g=cat(1,g1,g2,g3,g4,g5,g6,g7,g8,g9,g10,g11,g12,g13,g14,g15,g16,g17,g18,g19,g20 ,g21,g22,g23,g24,g25,g26,g27);m=mean([r,g])n=cov([r,g])3.求质心function [xmean, ymean] = center(bw)bw=bwfill(bw,'holes');area = bwarea(bw);[m n] =size(bw);bw=double(bw);xmean =0; ymean = 0;for i=1:m,for j=1:n,xmean = xmean + j*bw(i,j);ymean = ymean + i*bw(i,j);end;end;if(area==0)xmean=0;ymean=0;elsexmean = xmean/area;ymean = ymean/area;xmean = round(xmean);ymean = round(ymean);end4. 求偏转角度function [theta] = orient(bw,xmean,ymean) [m n] =size(bw);bw=double(bw);a = 0;b = 0;c = 0;for i=1:m,for j=1:n,a = a + (j - xmean)^2 * bw(i,j);b = b + (j - xmean) * (i - ymean) * bw(i,j);c = c + (i - ymean)^2 * bw(i,j);end;b = 2 * b;theta = atan(b/(a-c))/2;theta = theta*(180/pi); % 从幅度转换到角度5. 找区域边界function [left, right, up, down] = bianjie(A)[m n] = size(A);left = -1;right = -1;up = -1;down = -1;for j=1:n,for i=1:m,if (A(i,j) ~= 0)left = j;break;end;end;if (left ~= -1) break;end;end;for j=n:-1:1,for i=1:m,if (A(i,j) ~= 0)right = j;break;end;end;if (right ~= -1) break;end;for i=1:m,for j=1:n,if (A(i,j) ~= 0)up = i;break;end;end;if (up ~= -1)break;end;end;for i=m:-1:1,for j=1:n,if (A(i,j) ~= 0)down = i;break;end;end;if (down ~= -1)break;end;end;6. 求起始坐标function newcoord = checklimit(coord,maxval) newcoord = coord;if (newcoord<1)newcoord=1;end;if (newcoord>maxval)newcoord=maxval;end;7.模板匹配function [ccorr, mfit, RectCoord] = mobanpipei(mult, frontalmodel,ly,wx,cx, cy, angle)frontalmodel=rgb2gray(frontalmodel);model_rot = imresize(frontalmodel,[ly wx],'bilinear'); % 调整模板大小model_rot = imrotate(model_rot,angle,'bilinear'); % 旋转模板[l,r,u,d] = bianjie(model_rot); % 求边界坐标bwmodel_rot=imcrop(model_rot,[l u (r-l) (d-u)]); % 选择模板人脸区域[modx,mody] =center(bwmodel_rot); % 求质心[morig, norig] = size(bwmodel_rot);% 产生一个覆盖了人脸模板的灰度图像mfit = zeros(size(mult));mfitbw = zeros(size(mult));[limy, limx] = size(mfit);% 计算原图像中人脸模板的坐标startx = cx-modx;starty = cy-mody;endx = startx + norig-1;endy = starty + morig-1;startx = checklimit(startx,limx);starty = checklimit(starty,limy);endx = checklimit(endx,limx);endy = checklimit(endy,limy);for i=starty:endy,for j=startx:endx,mfit(i,j) = model_rot(i-starty+1,j-startx+1);end;end;ccorr = corr2(mfit,mult) % 计算相关度[l,r,u,d] = bianjie(bwmodel_rot);sx = startx+l;sy = starty+u;RectCoord = [sx sy (r-1) (d-u)]; % 产生矩形坐标8.主程序clear;[fname,pname]=uigetfile({'*.jpg';'*.bmp';'*.tif';'*.gif'},'Please choose a color picture...'); % 返回打开的图片名与图片路径名[u,v]=size(fname);y=fname(v); % 图片格式代表值switch ycase 0errordlg('You Should Load Image File First...','Warning...');case{'g';'G';'p';'P';'f';'F'}; % 图片格式若是JPG/jpg、BMP/bmp、TIF/tif 或者GIF/gif,才打开I=cat(2,pname,fname);Ori_Face=imread(I);subplot(2,3,1),imshow(Ori_Face);otherwiseerrordlg('You Should Load Image File First...','Warning...');endR=Ori_Face(:,:,1);G=Ori_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8型转换成double型处理G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;m=[ 0.4144,0.3174]; % 均值n=[0.0031,-0.0004;-0.0004,0.0003]; % 方差row=size(Ori_Face,1); % 行像素数column=size(Ori_Face,2); % 列像素数for i=1:rowfor j=1:columnif RGB(i,j)==0rr(i,j)=0;gg(i,j)=0;elserr(i,j)=R1(i,j)/RGB(i,j); % rgb归一化gg(i,j)=G1(i,j)/RGB(i,j);x=[rr(i,j),gg(i,j)];p(i,j)=exp((-0.5)*(x-m)*inv(n)*(x-m)'); % 皮肤概率服从高斯分布endendendsubplot(2,3,2);imshow(p); % 显示皮肤灰度图像low_pass=1/9*ones(3);image_low=filter2(low_pass, p); % 低通滤波去噪声subplot(2,3,3);imshow(image_low);% 自适应阀值程序previousSkin2 = zeros(i,j);changelist = [];for threshold = 0.55:-0.1:0.05two_value = zeros(i,j);two_value(find(image_low>threshold)) = 1;change = sum(sum(two_value - previousSkin2));changelist = [changelist change];previousSkin2 = two_value;end[C, I] = min(changelist);optimalThreshold = (7-I)*0.1two_value = zeros(i,j);two_value(find(image_low>optimalThreshold)) = 1; % 二值化subplot(2,3,4);imshow(two_value); % 显示二值图像frontalmodel=imread('E:\我的照片\人脸模板.jpg'); % 读入人脸模板照片FaceCoord=[];imsourcegray=rgb2gray(Ori_Face); % 将原照片转换为灰度图像[L,N]=bwlabel(two_value,8); % 标注二值图像中连接的部分,L为数据矩阵,N为颗粒的个数for i=1:N,[x,y]=find(bwlabel(two_value)==i); % 寻找矩阵中标号为i的行和列的下标bwsegment = bwselect(two_value,y,x,8); % 选择出第i个颗粒numholes = 1-bweuler(bwsegment,4); % 计算此区域的空洞数if (numholes >= 1) % 若此区域至少包含一个洞,则将其选出进行下一步运算RectCoord = -1;[m n] = size(bwsegment);[cx,cy]=center(bwsegment); % 求此区域的质心bwnohole=bwfill(bwsegment,'holes'); % 将洞封住(将灰度值赋为1)justface = uint8(double(bwnohole) .* double(imsourcegray));% 只在原照片的灰度图像中保留该候选区域angle = orient(bwsegment,cx,cy); % 求此区域的偏转角度bw = imrotate(bwsegment, angle, 'bilinear');bw = bwfill(bw,'holes');[l,r,u,d] =bianjie(bw);wx = (r - l +1); % 宽度ly = (d - u + 1); % 高度wratio = ly/wx % 高宽比if ((0.8<=wratio)&(wratio<=2))% 如果目标区域的高度/宽度比例大于0.8且小于2.0,则将其选出进行下一步运算S=ly*wx; % 计算包含此区域矩形的面积A=bwarea(bwsegment); % 计算此区域面积if (A/S>0.35)[ccorr,mfit, RectCoord] = mobanpipei(justface,frontalmodel,ly,wx, cx,cy, angle);endif (ccorr>=0.6)mfitbw=(mfit>=1);invbw = xor(mfitbw,ones(size(mfitbw)));source_with_hole = uint8(double(invbw) .* double(imsourcegray));final_image = uint8(double(source_with_hole) + double(mfit));subplot(2,3,5);imshow(final_image); % 显示覆盖了模板脸的灰度图像imsourcegray = final_image;subplot(2,3,6);imshow(Ori_Face); % 显示检测效果图end;if (RectCoord ~= -1)FaceCoord = [FaceCoord; RectCoord];endendendend% 在认为是人脸的区域画矩形[numfaces x] = size(FaceCoord);for i=1:numfaces,hd = rectangle('Position',FaceCoord(i,:));set(hd, 'edgecolor', 'y');end人脸检测是人脸识别、人机交互、智能视觉监控等工作的前提。
(完整版)基于matlab程序实现人脸识别
基于matlab程序实现人脸识别1.人脸识别流程1.1.1基本原理基于YCbCr颜色空间的肤色模型进行肤色分割。
在YCbCr色彩空间内对肤色进行了建模发现,肤色聚类区域在Cb—Cr子平面上的投影将缩减,与中心区域显著不同。
采用这种方法的图像分割已经能够较为精确的将人脸和非人脸分割开来。
1.1.2流程图人脸识别流程图读入原始图像将图像转化为YCbCr颜色空间利用肤色模型二值化图像并作形态学处理选取出二值图像中的白色区域,度量区域属性,筛选后得到所有矩形块否筛选特定区域(高度和宽度的比率在(0.6~2)之间,眼睛特征)是存储人脸的矩形区域特殊区域根据其他信息筛选,标记最终的人脸区域2.人脸识别程序(1)人脸和非人脸区域分割程序function result = skin(Y,Cb,Cr)%SKIN Summary of this function goes here% Detailed explanation goes herea=25.39;b=14.03;ecx=1.60;ecy=2.41;sita=2.53;cx=109.38;cy=152.02;xishu=[cos(sita) sin(sita);-sin(sita) cos(sita)];%如果亮度大于230,则将长短轴同时扩大为原来的1.1倍if(Y>230)a=1.1*a;b=1.1*b;end%根据公式进行计算Cb=double(Cb);Cr=double(Cr);t=[(Cb-cx);(Cr-cy)];temp=xishu*t;value=(temp(1)-ecx)^2/a^2+(temp(2)-ecy)^2/b^2;%大于1则不是肤色,返回0;否则为肤色,返回1if value>1result=0;elseresult=1;endend(2)人脸的确认程序function eye = findeye(bImage,x,y,w,h)%FINDEYE Summary of this function goes here % Detailed explanation goes herepart=zeros(h,w);%二值化for i=y:(y+h)for j=x:(x+w)if bImage(i,j)==0part(i-y+1,j-x+1)=255;elsepart(i-y+1,j-x+1)=0;endendend[L,num]=bwlabel(part,8);%如果区域中有两个以上的矩形则认为有眼睛if num<2eye=0;elseeye=1;endend(3)人脸识别主程序clear all;%读入原始图像I=imread('face3.jpg');gray=rgb2gray(I);ycbcr=rgb2ycbcr(I);%将图像转化为YCbCr空间heighth=size(gray,1);%读取图像尺寸width=size(gray,2);for i=1:heighth %利用肤色模型二值化图像for j=1:widthY=ycbcr(i,j,1);Cb=ycbcr(i,j,2);Cr=ycbcr(i,j,3);if(Y<80)gray(i,j)=0;elseif(skin(Y,Cb,Cr)==1)%根据色彩模型进行图像二值化gray(i,j)=255;elsegray(i,j)=0;endendendendse=strel('arbitrary',eye(5));%二值图像形态学处理gray=imopen(gray,se);figure;imshow(gray)[L,num]=bwlabel(gray,8);%采用标记方法选出图中的白色区域stats=regionprops(L,'BoundingBox');%度量区域属性n=1;%存放经过筛选以后得到的所有矩形块result=zeros(n,4);figure,imshow(I);hold on;for i=1:num %开始筛选特定区域box=stats(i).BoundingBox;x=box(1);%矩形坐标Xy=box(2);%矩形坐标Yw=box(3);%矩形宽度wh=box(4);%矩形高度hratio=h/w;%宽度和高度的比例ux=uint16(x);uy=uint8(y);if ux>1ux=ux-1;endif uy>1uy=uy-1;endif w<20 || h<20|| w*h<400 %矩形长宽的范围和矩形的面积可自行设定continueelseif ratio<2 && ratio>0.6 && findeye(gray,ux,uy,w,h)==1%根据“三庭五眼”规则高度和宽度比例应该在(0.6,2)内;result(n,:)=[ux uy w h];n=n+1;endendif size(result,1)==1 && result(1,1)>0 %对可能是人脸的区域进行标记rectangle('Position',[result(1,1),result(1,2),result(1,3),result(1,4)],'EdgeColor','r'); else%如果满足条件的矩形区域大于1,则再根据其他信息进行筛选a=0;arr1=[];arr2=[];for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%得到符合和人脸匹配的数据if m1+m3<width && m2+m4<heighth && m3<0.2*widtha=a+1;arr1(a)=m3;arr2(a)=m4;%rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endend%得到人脸长度和宽度的最小区域arr3=[];arr3=sort(arr1,'ascend');arr4=[];arr4=sort(arr2,'ascend');%根据得到的数据标定最终的人脸区域for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%最终标定人脸if m1+m3<width && m2+m4<heighth && m3<0.2*widthm3=arr3(1);m4=arr4(1);rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endendend(4)程序说明人脸识别程序主要包含三个程序模块,人脸识别主程序由三部分构成。
基于matlab的人脸识别
本科生毕业论文(设计)题目基于MATLAB的人脸识别姓名学号院系专业自动化指导教师职称2015年5月15日曲阜师范大学教务处制目录摘要 (1)关键词 (1)Abstract (1)K e y w o r d s (1)1 绪论 (2)1.1 基本介绍与概念 (2)1.2 研发历史与发展现状 (3)1.3 研究背景与意义 (3)2 人脸检测 (4)2.1 检测的具体步骤 (4)2.1 YCbCr空间 (4)2.2 灰度图像转换 (4)2.3 噪声消除 (5)2.4 图像填孔 (5)2.5 图像重构 (5)2.6 边缘检测 (6)2.7 利用规则确定人脸 (6)3 人脸识别 (7)3.1 人脸识别的步骤 (7)3.2 K-L变换原理 (7)3.3 K-L变换 (7)3.4 图像特征脸基底的确立 (8)3.5 图像的识别 (9)4 MATLAB仿真功能的实现 (10)4.1 系统仿真综述 (10)4.2选择预存人脸数据库 (10)4.3 创建预存人脸向量库T (13)4.4 求特征脸空间 (14)4.5人脸识别 (15)4.6 人脸识别结果显示 (16)5 结果分析 (17)6 结论 (18)致谢 (19)参考文献 (19)附录: (20)基于MATLAB的人脸识别自动化专业学生指导老师摘要:人脸识别起始于上个世纪60年代,具有广泛的应用前景,它的工作原理是借由个体的生物特征来确认生物个体,文章利用MATLAB软件实现人脸信息的检测与识别,在输入的图像中寻找人脸区域,把图像分割成两个部分——人脸区域和非人脸区域,之后与设定的人脸库进行特征值比较,辨识出人脸代表的身份。
文章利用YCbCr空间以及二值图像实现人脸边缘分割,用霍特林变换(Kaehunen-Love Transform,K-L)以及主成分分析(Principal Component Analysis,PCA)算法对人脸进行识别对比,并详细介绍了K-L的推导过程,并在MATLAB上对PCA人脸识别算法进行仿真。
基于某matlab程序实现人脸识别
基于matlab程序实现人脸识别1.人脸识别流程1.1.1基本原理基于YCbCr颜色空间的肤色模型进行肤色分割。
在YCbCr色彩空间内对肤色进行了建模发现,肤色聚类区域在Cb—Cr子平面上的投影将缩减,与中心区域显著不同。
采用这种方法的图像分割已经能够较为精确的将人脸和非人脸分割开来。
1.1.2流程图人脸识别流程图读入原始图像将图像转化为YCbCr颜色空间利用肤色模型二值化图像并作形态学处理选取出二值图像中的白色区域,度量区域属性,筛选后得到所有矩形块否筛选特定区域(高度和宽度的比率在(0.6~2)之间,眼睛特征)是存储人脸的矩形区域特殊区域根据其他信息筛选,标记最终的人脸区域2.人脸识别程序(1)人脸和非人脸区域分割程序function result = skin(Y,Cb,Cr)%SKIN Summary of this function goes here% Detailed explanation goes herea=25.39;b=14.03;ecx=1.60;ecy=2.41;sita=2.53;cx=109.38;cy=152.02;xishu=[cos(sita) sin(sita);-sin(sita) cos(sita)]; %如果亮度大于230,则将长短轴同时扩大为原来的1.1倍if(Y>230)a=1.1*a;b=1.1*b;end%根据公式进行计算Cb=double(Cb);Cr=double(Cr);t=[(Cb-cx);(Cr-cy)];temp=xishu*t;value=(temp(1)-ecx)^2/a^2+(temp(2)-ecy)^2/b^2;%大于1则不是肤色,返回0;否则为肤色,返回1if value>1result=0;elseresult=1;endend(2)人脸的确认程序function eye = findeye(bImage,x,y,w,h)%FINDEYE Summary of this function goes here % Detailed explanation goes herepart=zeros(h,w);%二值化for i=y:(y+h)for j=x:(x+w)if bImage(i,j)==0part(i-y+1,j-x+1)=255;elsepart(i-y+1,j-x+1)=0;endendend[L,num]=bwlabel(part,8);%如果区域中有两个以上的矩形则认为有眼睛if num<2eye=0;elseeye=1;endend(3)人脸识别主程序clear all;%读入原始图像I=imread('face3.jpg');gray=rgb2gray(I);ycbcr=rgb2ycbcr(I);%将图像转化为YCbCr空间heighth=size(gray,1);%读取图像尺寸width=size(gray,2);for i=1:heighth %利用肤色模型二值化图像for j=1:widthY=ycbcr(i,j,1);Cb=ycbcr(i,j,2);Cr=ycbcr(i,j,3);if(Y<80)gray(i,j)=0;elseif(skin(Y,Cb,Cr)==1)%根据色彩模型进行图像二值化 gray(i,j)=255;elsegray(i,j)=0;endendendendse=strel('arbitrary',eye(5));%二值图像形态学处理gray=imopen(gray,se);figure;imshow(gray)[L,num]=bwlabel(gray,8);%采用标记方法选出图中的白色区域stats=regionprops(L,'BoundingBox');%度量区域属性n=1;%存放经过筛选以后得到的所有矩形块result=zeros(n,4);figure,imshow(I);hold on;for i=1:num %开始筛选特定区域box=stats(i).BoundingBox;x=box(1);%矩形坐标Xy=box(2);%矩形坐标Yw=box(3);%矩形宽度wh=box(4);%矩形高度hratio=h/w;%宽度和高度的比例ux=uint16(x);uy=uint8(y);if ux>1ux=ux-1;endif uy>1uy=uy-1;endif w<20 || h<20|| w*h<400 %矩形长宽的范围和矩形的面积可自行设定continueelseif ratio<2 && ratio>0.6 && findeye(gray,ux,uy,w,h)==1 %根据“三庭五眼”规则高度和宽度比例应该在(0.6,2)内;result(n,:)=[ux uy w h];n=n+1;endendif size(result,1)==1 && result(1,1)>0 %对可能是人脸的区域进行标记rectangle('Position',[result(1,1),result(1,2),result(1,3),result(1,4) ],'EdgeColor','r');else%如果满足条件的矩形区域大于1,则再根据其他信息进行筛选arr1=[];arr2=[];for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%得到符合和人脸匹配的数据if m1+m3<width && m2+m4<heighth && m3<0.2*widtha=a+1;arr1(a)=m3;arr2(a)=m4;%rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endend%得到人脸长度和宽度的最小区域arr3=[];arr3=sort(arr1,'ascend');arr4=[];arr4=sort(arr2,'ascend');%根据得到的数据标定最终的人脸区域for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%最终标定人脸if m1+m3<width && m2+m4<heighth && m3<0.2*widthm3=arr3(1);m4=arr4(1);rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endend(4)程序说明人脸识别程序主要包含三个程序模块,人脸识别主程序由三部分构成。
《基于MATLAB的人脸识别算法的研究》范文
《基于MATLAB的人脸识别算法的研究》篇一一、引言人脸识别技术是计算机视觉领域的重要分支,随着科技的发展和大数据的普及,其在安全监控、身份认证、智能交互等领域得到了广泛的应用。
本文旨在基于MATLAB平台,研究并分析几种常见的人脸识别算法,并对其性能进行对比与评价。
二、人脸识别算法概述人脸识别算法主要包括基于特征的人脸识别算法和基于深度学习的人脸识别算法两大类。
其中,基于特征的人脸识别算法如主成分分析(PCA)、线性判别分析(LDA)、局部二值模式(LBP)等,通过提取人脸特征进行识别;而基于深度学习的人脸识别算法如卷积神经网络(CNN)等,通过深度学习技术自动提取人脸特征并进行识别。
三、基于MATLAB的人脸识别算法实现1. 数据准备:使用MATLAB的Image Acquisition Toolbox获取人脸图像数据,并进行预处理,包括灰度化、归一化等操作。
2. 特征提取:采用PCA、LDA等算法提取人脸特征。
在MATLAB中,可以利用其内置的函数或编写自定义函数进行特征提取。
3. 分类器设计:根据提取的特征,设计分类器进行人脸识别。
在MATLAB中,可以使用其内置的分类器函数或自行设计分类器。
4. 算法实现:将上述步骤组合起来,实现基于MATLAB的人脸识别算法。
四、常见人脸识别算法的比较与分析1. PCA算法:PCA是一种常用的特征提取方法,能够有效地降低数据的维度,提高识别的速度和准确性。
但PCA算法对光照、表情等因素的敏感性较高,需要结合其他技术进行优化。
2. LDA算法:LDA算法通过最大化类间距离和最小化类内距离来提取特征,具有较好的分类性能。
但LDA算法对样本数量的要求较高,样本数量不足时可能导致性能下降。
3. CNN算法:CNN是一种基于深度学习的人脸识别算法,能够自动提取人脸特征并进行识别。
CNN算法具有较高的准确性和鲁棒性,但需要大量的训练数据和计算资源。
五、实验与结果分析为了验证上述人脸识别算法的性能,我们进行了多组实验。
MATLAB人脸识别源代码
MATLAB人脸识别源代码% FaceRec.m %CQUPT% PCA 识别率88%% calc xmean,sigma and its eigen decompositionallsamples=[];%所有训练图片for i=1:40for j=1:5a=imread(strcat('e:\ORL\s',num2str(i),'\',num2str(j),'.pgm'));b=a(1:112*92); %b是行矢量1*N,N=10304,提取顺序是先列后行,%即从上到下,从左到右b=double(b);allsamples=[allsamples;b]; %allsamples是一个M*N矩阵,allsamples中每一行数据代%表一张图片,其中M=200endendsamplemean=mean(allsamples); %平均图片,1*N for i=1:200xmean(i,:)=allsamples(i,:)-samplemean; %allsamples是一个M*N矩阵,allsamples中每一行保存的数据是“每个图片数据—平均图片”end;%获取特征植及特征向量sigma=xmean*xmean'; % M* M矩阵[v d]=eig(sigma);d1=diag(d);%按特征值大小以降序排列dsort=flipud(d1);vsort=fliplr(v);%以下选择90%的能量dsum=sum(dsort);dsum_extract=0;p=0;while(dsum_extract/dsum<0.9) p=p+1;dsum_extract=sum(dsort(1:p)); endi=1;% (训练阶段)计算特征脸形成的坐标系base = xmean' * vsort(:,1:p) * diag(dsort(1:p).^(-1/2));%base是N*p阶矩阵,除以dsort(i) ^(-1/2))是对人脸图象的标准化(是其方差为1)% xmean' * vsort(:,1:p)是小矩阵的特征向量向大矩阵特征向量转换的过程%以下两行将训练样本对坐标系上进行投影,得到一个M*p子空间中的一个点,%即在子空间中的组合系数allcoor=allsamples*base;accu = 0; %下面的人脸识别过程中就是利用这些组合系数来进行识别%测试过程for i=1:40for j=6:10 %读入40 x 5 副测试图像a=imread(strcat('e:\ORL\s',num2str(i),'\',num2str(j),'.pgm'));b=a(1:10304);b=double(b);tcoor=b*base; %计算坐标,是1*p阶矩阵for k=1:200mdist(k)=norm(tcoor-allcoor(k,:)); end;%三阶近邻[dist,index2]=sort(mdist); class1=floor( (index2(1)-1)/5 )+1;class2=floor((index2(2)-1)/5)+1;class3=floor((index2(3)-1)/5)+1; if class1~=class2 && class2~=class3 class=class1;elseif class1==class2class=class1;elseif class2==class3class=class2;end;if class==iaccu=accu+1;end;end;end;accuracy=accu/200 % 输出识别率% FaceRec.m %CQUPT% PCA 识别率88%% calc xmean,sigma and its eigen decompositionallsamples=[]; %所有训练图片for i=1:40for j=1:5a=imread(strcat('e:\ORL\s',num2str(i),'\',num2str(j),'.pgm'));b=a(1:112*92); %b是行矢量1*N,N=10304,提取顺序是先列后行,%即从上到下,从左到右b=double(b);allsamples=[allsamples;b]; %allsamples是一个M*N矩阵,allsamples中每一行数据代%表一张图片,其中M=200endendsamplemean=mean(allsamples); %平均图片,1*Nfor i=1:200 xmean(i,:)=allsamples(i,:)-samplemean; %allsamples是一个M*N矩阵,allsamples中每一行保存 %的数据是“每个图片数据—平均图片” end;%获取特征植及特征向量sigma=xmean*xmean'; % M* M矩阵 [v d]=eig(sigma); d1=diag(d);%按特征值大小以降序排列dsort=flipud(d1); vsort=fliplr(v); %以下选择90%的能量dsum=sum(dsort);dsum_extract=0;p=0;while(dsum_extract/dsum<0.9) p=p+1;dsum_extract=sum(dsort(1:p)); endp=199;% (训练阶段)计算特征脸形成的坐标系base = xmean' * vsort(:,1:p) * diag(dsort(1:p).^(-1/2));%生成特征脸for(k=1:p)temp=reshape(base(:,k),112,92); newpath=[…e:\test\? int2str(k)….jpg?];imwrite(mat2gray(temp), newpath); end%将模型保存Save(…e:\ORL\model.mat? ,?base?, …samplemean?);%Reconstruct.m % CQUPTFunction[]=reconstruct() Load e:\ORL\model.mat;%计算新图片在特征子空间中的系数Img=?D:\test2\10.jpg?A=imread(img);b=a(1:112*92); % b是行矢量 1*N,其中N =10304 b=double(b);b=b-samplemean;c = b * base; % c 是图片 a在子空间中的系数, 是 1*p 行矢量 % 根据特征系数及特征脸重建图% 前15 个t = 15;temp = base(:,1:t) * c(1:t)'; temp = temp + samplemean';imwrite(mat2gray(reshape(temp, 112,92)),'d:\test2\t1.jpg');% 前50个t = 50;temp = base(:,1:t) * c(1:t)'; temp = temp + samplemean';imwrite(mat2gray(reshape(temp, 112,92)),'d:\test2\t2.jpg');% 前 100个t = 100;temp = base(:,1:t) * c(1:t)'; temp = temp + samplemean';imwrite(mat2gray(reshape(temp, 112,92)),'d:\test2\t3.jpg');% 前150个t = 150;temp = base(:,1:t) * c(1:t)'; temp = temp + samplemean';imwrite(mat2gray(reshape(temp, 112,92)),'d:\test2\t4.jpg');% 前199 个t = 199;temp = base(:,1:t) * c(1:t)'; temp = temp + samplemean';imwrite(mat2gray(reshape(temp, 112,92)),'d:\test2\t5.jpg');图片标准化通常是一个整体概念,要求把图片归一到均值为0,方差为1的情况下。
基于matlab程序实现人脸识别
For personal use only in study andresearch; not for commercial use基于matlab程序实现人脸识别1.人脸识别流程基于YCbCr颜色空间的肤色模型进行肤色分割。
在YCbCr色彩空间内对肤色进行了建模发现,肤色聚类区域在Cb—Cr子平面上的投影将缩减,与中心区域显着不同。
采用这种方法的图像分割已经能够较为精确的将人脸和非人脸分割开来。
人脸识别流程图2.人脸识别程序(1)人脸和非人脸区域分割程序function result = skin(Y,Cb,Cr)%SKIN Summary of this function goes here% Detailed explanation goes herea=25.39;b=14.03;ecx=1.60;ecy=2.41;sita=2.53;cx=109.38;cy=152.02;xishu=[cos(sita) sin(sita);-sin(sita) cos(sita)];%如果亮度大于230,则将长短轴同时扩大为原来的1.1倍if(Y>230)a=1.1*a;b=1.1*b;end%根据公式进行计算Cb=double(Cb);Cr=double(Cr);t=[(Cb-cx);(Cr-cy)];temp=xishu*t;value=(temp(1)-ecx)^2/a^2+(temp(2)-ecy)^2/b^2;%大于1则不是肤色,返回0;否则为肤色,返回1if value>1result=0;elseresult=1;endend(2)人脸的确认程序function eye = findeye(bImage,x,y,w,h)%FINDEYE Summary of this function goes here % Detailed explanation goes herepart=zeros(h,w);%二值化for i=y:(y+h)for j=x:(x+w)if bImage(i,j)==0part(i-y+1,j-x+1)=255;elsepart(i-y+1,j-x+1)=0;endendend[L,num]=bwlabel(part,8);%如果区域中有两个以上的矩形则认为有眼睛if num<2eye=0;elseeye=1;endend(3)人脸识别主程序clear all;%读入原始图像I=imread('face3.jpg');gray=rgb2gray(I);ycbcr=rgb2ycbcr(I);%将图像转化为YCbCr空间heighth=size(gray,1);%读取图像尺寸width=size(gray,2);for i=1:heighth %利用肤色模型二值化图像for j=1:widthY=ycbcr(i,j,1);Cb=ycbcr(i,j,2);Cr=ycbcr(i,j,3);if(Y<80)gray(i,j)=0;elseif(skin(Y,Cb,Cr)==1)%根据色彩模型进行图像二值化gray(i,j)=255;elsegray(i,j)=0;endendendendse=strel('arbitrary',eye(5));%二值图像形态学处理gray=imopen(gray,se);figure;imshow(gray)[L,num]=bwlabel(gray,8);%采用标记方法选出图中的白色区域stats=regionprops(L,'BoundingBox');%度量区域属性n=1;%存放经过筛选以后得到的所有矩形块result=zeros(n,4);figure,imshow(I);hold on;for i=1:num %开始筛选特定区域box=stats(i).BoundingBox;x=box(1);%矩形坐标Xy=box(2);%矩形坐标Yw=box(3);%矩形宽度wh=box(4);%矩形高度hratio=h/w;%宽度和高度的比例ux=uint16(x);uy=uint8(y);if ux>1ux=ux-1;endif uy>1uy=uy-1;endif w<20 || h<20|| w*h<400 %矩形长宽的范围和矩形的面积可自行设定continueelseif ratio<2 && ratio>0.6 && findeye(gray,ux,uy,w,h)==1%根据“三庭五眼”规则高度和宽度比例应该在(0.6,2)内;result(n,:)=[ux uy w h];n=n+1;endendif size(result,1)==1 && result(1,1)>0 %对可能是人脸的区域进行标记rectangle('Position',[result(1,1),result(1,2),result(1,3),result(1,4)],'EdgeColor','r'); else%如果满足条件的矩形区域大于1,则再根据其他信息进行筛选a=0;arr1=[];arr2=[];for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%得到符合和人脸匹配的数据if m1+m3<width && m2+m4<heighth && m3<0.2*width a=a+1;arr1(a)=m3;arr2(a)=m4;%rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endend%得到人脸长度和宽度的最小区域arr3=[];arr3=sort(arr1,'ascend');arr4=[];arr4=sort(arr2,'ascend');%根据得到的数据标定最终的人脸区域for m=1:size(result,1)m1=result(m,1);m2=result(m,2);m3=result(m,3);m4=result(m,4);%最终标定人脸if m1+m3<width && m2+m4<heighth && m3<0.2*widthm3=arr3(1);m4=arr4(1);rectangle('Position',[m1,m2,m3,m4],'EdgeColor','r');endendend(4)程序说明人脸识别程序主要包含三个程序模块,人脸识别主程序由三部分构成。
根据matlab的人脸识别源代码
function varargout = FR_Processed_histogram(varargin)%这种算法是基于直方图处理的方法%The histogram of image is calculated and then bin formation is done on the%basis of mean of successive graylevels frequencies. The training is done on odd images of 40 subjects (200 images out of 400 images)%The results of the implemented algorithm is 99.75 (recognition fails on image number 4 of subject 17)gui_Singleton = 1;gui_State = struct('gui_Name', mfilename, ...'gui_Singleton', gui_Singleton, ...'gui_OpeningFcn',@FR_Processed_histogram_OpeningFcn, ...'gui_OutputFcn',@FR_Processed_histogram_OutputFcn, ...'gui_LayoutFcn', [] , ...'gui_Callback', []);if nargin && ischar(varargin{1})gui_State.gui_Callback = str2func(varargin{1});endif nargout[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});elsegui_mainfcn(gui_State, varargin{:});end% End initialization code - DO NOT EDIT%--------------------------------------------------------------------------% --- Executes just before FR_Processed_histogram is made visible.function FR_Processed_histogram_OpeningFcn(hObject, eventdata, handles, varargin)% This function has no output args, see OutputFcn.% hObject handle to figure% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA) % varargin command line arguments to FR_Processed_histogram (see VARARGIN)% Choose default command line output for FR_Processed_histogramhandles.output = hObject;% Update handles structureguidata(hObject, handles);% UIWAIT makes FR_Processed_histogram wait for user response (see UIRESUME)% uiwait(handles.figure1);global total_sub train_img sub_img max_hist_level bin_num form_bin_num;total_sub = 40;train_img = 200;sub_img = 10;max_hist_level = 256;bin_num = 9;form_bin_num = 29;%--------------------------------------------------------------------------% --- Outputs from this function are returned to the command line.function varargout = FR_Processed_histogram_OutputFcn(hObject, eventdata, handles)% varargout cell array for returning output args (see VARARGOUT);% hObject handle to figure% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA)% Get default command line output from handles structurevarargout{1} = handles.output;%--------------------------------------------------------------------------% --- Executes on button press in train_button.function train_button_Callback(hObject, eventdata, handles)% hObject handle to train_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA)global train_processed_bin;global total_sub train_img sub_img max_hist_level bin_num form_bin_num;train_processed_bin(form_bin_num,train_img) = 0;K = 1;train_hist_img = zeros(max_hist_level, train_img);for Z=1:1:total_subfor X=1:2:sub_img %%%train on odd number of images of each subjectI = imread( strcat('ORL\S',int2str(Z),'\',int2str(X),'.bmp') );[rows cols] = size(I);for i=1:1:rowsfor j=1:1:colsif( I(i,j) == 0 )train_hist_img(max_hist_level, K) = train_hist_img(max_hist_level, K) + 1;elsetrain_hist_img(I(i,j), K) = train_hist_img(I(i,j), K) + 1;endendendK = K + 1;endend[r c] = size(train_hist_img);sum = 0;for i=1:1:cK = 1;for j=1:1:rif( (mod(j,bin_num)) == 0 )sum = sum + train_hist_img(j,i);train_processed_bin(K,i) = sum/bin_num;K = K + 1;sum = 0;elsesum = sum + train_hist_img(j,i);endendtrain_processed_bin(K,i) = sum/bin_num;enddisplay ('Training Done')save 'train'train_processed_bin;%--------------------------------------------------------------------------% --- Executes on button press in Testing_button.function Testing_button_Callback(hObject, eventdata, handles)% hObject handle to Testing_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA) global train_img max_hist_level bin_num form_bin_num;global train_processed_bin;global filename pathname Iload 'train'test_hist_img(max_hist_level) = 0;test_processed_bin(form_bin_num) = 0;[rows cols] = size(I);for i=1:1:rowsfor j=1:1:colsif( I(i,j) == 0 )test_hist_img(max_hist_level) =test_hist_img(max_hist_level) + 1;elsetest_hist_img(I(i,j)) = test_hist_img(I(i,j)) + 1;endendend[r c] = size(test_hist_img);sum = 0;K = 1;for j=1:1:cif( (mod(j,bin_num)) == 0 )sum = sum + test_hist_img(j);test_processed_bin(K) = sum/bin_num;K = K + 1;sum = 0;elsesum = sum + test_hist_img(j);endendtest_processed_bin(K) = sum/bin_num;sum = 0;K = 1;for y=1:1:train_imgfor z=1:1:form_bin_numsum = sum + abs( test_processed_bin(z) - train_processed_bin(z,y) );endimg_bin_hist_sum(K,1) = sum;sum = 0;K = K + 1;end[temp M] = min(img_bin_hist_sum);M = ceil(M/5);getString_start=strfind(pathname,'S');getString_start=getString_start(end)+1;getString_end=strfind(pathname,'\');getString_end=getString_end(end)-1;subjectindex=str2num(pathname(getString_start:getString_end));if (subjectindex == M)axes (handles.axes3)%image no: 5 is shown for visualization purposeimshow(imread(STRCAT('ORL\S',num2str(M),'\5.bmp')))msgbox ( 'Correctly Recognized');elsedisplay ([ 'Error==> Testing Image of Subject >>' num2str(subjectindex) ' matches with the image of subject >> ' num2str(M)])axes (handles.axes3)%image no: 5 is shown for visualization purposeimshow(imread(STRCAT('ORL\S',num2str(M),'\5.bmp')))msgbox ( 'Incorrectly Recognized');enddisplay('Testing Done')%--------------------------------------------------------------------------function box_Callback(hObject, eventdata, handles)% hObject handle to box (see GCBO)% eventdata reserved - to be defined in a future version ofMATLAB% handles structure with handles and user data (see GUIDATA)% Hints: get(hObject,'String') returns contents of box as text% str2double(get(hObject,'String')) returns contents of box as a double%--------------------------------------------------------------------------% --- Executes during object creation, after setting all properties.function box_CreateFcn(hObject, eventdata, handles)% hObject handle to box (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles empty - handles not created until after all CreateFcns called% Hint: edit controls usually have a white background on Windows.% See ISPC and COMPUTER.if ispc && isequal(get(hObject,'BackgroundColor'), get(0,'defaultUicontrolBackgroundColor'))set(hObject,'BackgroundColor','white');end%--------------------------------------------------------------------------% --- Executes on button press in Input_Image_button.function Input_Image_button_Callback(hObject, eventdata, handles) % hObject handle to Input_Image_button (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA) global filename pathname I[filename, pathname] = uigetfile('*.bmp', 'Test Image');axes(handles.axes1)imgpath=STRCAT(pathname,filename);I = imread(imgpath);imshow(I)%--------------------------------------------------------------------------% --- Executes during object creation, after setting all properties.function axes3_CreateFcn(hObject, eventdata, handles)% hObject handle to axes3 (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles empty - handles not created until after all CreateFcnscalled% Hint: place code in OpeningFcn to populate axes3 %Programmed by Usman Qayyum。
基于MATLAB的人脸识别源程序文件
1.色彩空间转换function [r,g]=rgb_RGB(Ori_Face)R=Ori_Face(:,:,1);G=Ori_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8型转换成double型G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;row=size(Ori_Face,1); % 行像素column=size(Ori_Face,2); % 列像素for i=1:rowfor j=1:columnrr(i,j)=R1(i,j)/RGB(i,j);gg(i,j)=G1(i,j)/RGB(i,j);endendrrr=mean(rr);r=mean(rrr);ggg=mean(gg);g=mean(ggg);2.均值和协方差t1=imread('D:\matlab\皮肤库\1.jpg');[r1,g1]=rgb_RGB(t1);t2=imread('D:\matlab\皮肤库\2.jpg');[r2,g2]=rgb_RGB(t2);t3=imread('D:\matlab\皮肤库\3.jpg');[r3,g3]=rgb_RGB(t3);t4=imread('D:\matlab\皮肤库\4.jpg');[r4,g4]=rgb_RGB(t4);t5=imread('D:\matlab\皮肤库\5.jpg');[r5,g5]=rgb_RGB(t5);t6=imread('D:\matlab\皮肤库\6.jpg');[r6,g6]=rgb_RGB(t6);t7=imread('D:\matlab\皮肤库\7.jpg');[r7,g7]=rgb_RGB(t7);t8=imread('D:\matlab\皮肤库\8.jpg');[r8,g8]=rgb_RGB(t8);t9=imread('D:\matlab\皮肤库\9.jpg');[r9,g9]=rgb_RGB(t9);t10=imread('D:\matlab\皮肤库\10.jpg');[r10,g10]=rgb_RGB(t10);t11=imread('D:\matlab\皮肤库\11.jpg');[r11,g11]=rgb_RGB(t11);t12=imread('D:\matlab\皮肤库\12.jpg');[r12,g12]=rgb_RGB(t12);t13=imread('D:\matlab\皮肤库\13.jpg');[r13,g13]=rgb_RGB(t13);t14=imread('D:\matlab\皮肤库\14.jpg');[r14,g14]=rgb_RGB(t14);t15=imread('D:\matlab\皮肤库\15.jpg');[r15,g15]=rgb_RGB(t15);t16=imread('D:\matlab\皮肤库t17=imread('D:\matlab\皮肤库\17.jpg');[r17,g17]=rgb_RGB(t17);t18=imread('D:\matlab\皮肤库\18.jpg');[r18,g18]=rgb_RGB(t18);t19=imread('D:\matlab\皮肤库\19.jpg');[r19,g19]=rgb_RGB(t19);t20=imread('D:\matlab\皮肤库\20.jpg');[r20,g20]=rgb_RGB(t20);t21=imread('D:\matlab\皮肤库\21.jpg');[r21,g21]=rgb_RGB(t21);t22=imread('D:\matlab\皮肤库\22.jpg');[r22,g22]=rgb_RGB(t22);t23=imread('D:\matlab\皮肤库\23.jpg');[r23,g23]=rgb_RGB(t23);t24=imread('D:\matlab\皮肤库\24.jpg');[r24,g24]=rgb_RGB(t24);t25=imread('D:\matlab\皮肤库\25.jpg');[r25,g25]=rgb_RGB(t25);t26=imread('D:\matlab\皮肤库\26.jpg');[r26,g26]=rgb_RGB(t26);t27=imread('D:\matlab\皮肤库r=cat(1,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,r13,r14,r15, r16,r17,r18,r19,r20,r21,r22,r23,r24,r25,r26,r27);g=cat(1,g1,g2,g3,g4,g5,g6,g7,g8,g9,g10,g11,g12,g13,g14,g15, g16,g17,g18,g19,g20,g21,g22,g23,g24,g25,g26,g27);m=mean([r,g])n=cov([r,g])3.求质心function [xmean, ymean] = center(bw)bw=bwfill(bw,'holes');area = bwarea(bw);[m n] =size(bw);bw=double(bw);xmean =0; ymean = 0;for i=1:m,for j=1:n,xmean = xmean + j*bw(i,j);ymean = ymean + i*bw(i,j);end;end;if(area==0)xmean=0;ymean=0;elsexmean = xmean/area;ymean = ymean/area;xmean = round(xmean);ymean = round(ymean);end4. 求偏转角度function [theta] = orient(bw,xmean,ymean) [m n] =size(bw);bw=double(bw);a = 0;b = 0;c = 0;for i=1:m,for j=1:n,a = a + (j - xmean)^2 * bw(i,j);b = b + (j - xmean) * (i - ymean) * bw(i,j);c = c + (i - ymean)^2 * bw(i,j);end;end;b = 2 * b;theta = atan(b/(a-c))/2;theta = theta*(180/pi); % 从幅度转换到角度5. 找区域边界function [left, right, up, down] = bianjie(A) [m n] = size(A);left = -1;right = -1;up = -1;down = -1;for j=1:n,for i=1:m,if (A(i,j) ~= 0)left = j;break;end;end;if (left ~= -1) break;end;end;for j=n:-1:1,for i=1:m,if (A(i,j) ~= 0)right = j;break;end;end;if (right ~= -1) break; end;end;for i=1:m,for j=1:n,if (A(i,j) ~= 0)up = i;break;end;end;if (up ~= -1)break;end;end;for i=m:-1:1,for j=1:n,if (A(i,j) ~= 0) down = i;break;end;end;if (down ~= -1)break;end;end;6. 求起始坐标function newcoord = checklimit(coord,maxval)newcoord = coord;if (newcoord<1)newcoord=1;end;if (newcoord>maxval)newcoord=maxval;end;7.模板匹配function [ccorr, mfit, RectCoord] = mobanpipei(mult, frontalmodel,ly,wx,cx, cy, angle)frontalmodel=rgb2gray(frontalmodel);model_rot = imresize(frontalmodel,[ly wx],'bilinear'); % 调整模板大小model_rot = imrotate(model_rot,angle,'bilinear'); % 旋转模板[l,r,u,d] = bianjie(model_rot); % 求边界坐标bwmodel_rot=imcrop(model_rot,[l u (r-l) (d-u)]); % 选择模板人脸区域[modx,mody] =center(bwmodel_rot); % 求质心[morig, norig] = size(bwmodel_rot);% 产生一个覆盖了人脸模板的灰度图像mfit = zeros(size(mult));mfitbw = zeros(size(mult));[limy, limx] = size(mfit);% 计算原图像中人脸模板的坐标startx = cx-modx;starty = cy-mody;endx = startx + norig-1;endy = starty + morig-1;startx = checklimit(startx,limx);starty = checklimit(starty,limy);endx = checklimit(endx,limx);endy = checklimit(endy,limy);for i=starty:endy,for j=startx:endx,mfit(i,j) = model_rot(i-starty+1,j-startx+1);end;end;ccorr = corr2(mfit,mult) % 计算相关度[l,r,u,d] = bianjie(bwmodel_rot);sx = startx+l;sy = starty+u;RectCoord = [sx sy (r-1) (d-u)]; % 产生矩形坐标8.主程序clear;[fname,pname]=uigetfile({'*.jpg';'*.bmp';'*.tif';'*.gif'},' Please choose a color picture...'); % 返回打开的图片名与图片路径名[u,v]=size(fname);y=fname(v); % 图片格式代表值switch ycase 0errordlg('You Should Load Image File First...','Warning...');case{'g';'G';'p';'P';'f';'F'}; % 图片格式若是JPG/jpg、BMP/bmp、TIF/tif或者GIF/gif,才打开I=cat(2,pname,fname);Ori_Face=imread(I);subplot(2,3,1),imshow(Ori_Face);otherwiseerrordlg('You Should Load Image File First...','Warning...');endR=Ori_Face(:,:,1);G=Ori_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8型转换成double型处理G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;m=[ 0.4144,0.3174]; % 均值n=[0.0031,-0.0004;-0.0004,0.0003]; % 方差row=size(Ori_Face,1); % 行像素数column=size(Ori_Face,2); % 列像素数for i=1:rowfor j=1:columnif RGB(i,j)==0rr(i,j)=0;gg(i,j)=0;elserr(i,j)=R1(i,j)/RGB(i,j); % rgb归一化 gg(i,j)=G1(i,j)/RGB(i,j);x=[rr(i,j),gg(i,j)];p(i,j)=exp((-0.5)*(x-m)*inv(n)*(x-m)'); % 皮肤概率服从高斯分布endendendsubplot(2,3,2);imshow(p); % 显示皮肤灰度图像low_pass=1/9*ones(3);image_low=filter2(low_pass, p); % 低通滤波去噪声subplot(2,3,3);imshow(image_low);% 自适应阀值程序previousSkin2 = zeros(i,j);changelist = [];for threshold = 0.55:-0.1:0.05two_value = zeros(i,j);two_value(find(image_low>threshold)) = 1;change = sum(sum(two_value - previousSkin2));changelist = [changelist change];previousSkin2 = two_value;end[C, I] = min(changelist);optimalThreshold = (7-I)*0.1two_value = zeros(i,j);two_value(find(image_low>optimalThreshold)) = 1; % 二值化subplot(2,3,4);imshow(two_value); % 显示二值图像frontalmodel=imread('E:\我的照片\人脸模板.jpg'); % 读入人脸模板照片FaceCoord=[];imsourcegray=rgb2gray(Ori_Face); % 将原照片转换为灰度图像[L,N]=bwlabel(two_value,8); % 标注二值图像中连接的部分,L 为数据矩阵,N为颗粒的个数for i=1:N,[x,y]=find(bwlabel(two_value)==i); % 寻找矩阵中标号为i的行和列的下标bwsegment = bwselect(two_value,y,x,8); % 选择出第i个颗粒numholes = 1-bweuler(bwsegment,4); % 计算此区域的空洞数if (numholes >= 1) % 若此区域至少包含一个洞,则将其选出进行下一步运算RectCoord = -1;[m n] = size(bwsegment);[cx,cy]=center(bwsegment); % 求此区域的质心bwnohole=bwfill(bwsegment,'holes'); % 将洞封住(将灰度值赋为1)justface = uint8(double(bwnohole) .* double(imsourcegray)); % 只在原照片的灰度图像中保留该候选区域angle = orient(bwsegment,cx,cy); % 求此区域的偏转角度bw = imrotate(bwsegment, angle, 'bilinear');bw = bwfill(bw,'holes');[l,r,u,d] =bianjie(bw);wx = (r - l +1); % 宽度ly = (d - u + 1); % 高度wratio = ly/wx % 高宽比if ((0.8<=wratio)&(wratio<=2))% 如果目标区域的高度/宽度比例大于0.8且小于2.0,则将其选出进行下一步运算S=ly*wx; % 计算包含此区域矩形的面积A=bwarea(bwsegment); % 计算此区域面积if (A/S>0.35)[ccorr,mfit, RectCoord] = mobanpipei(justface,frontalmodel,ly,wx, cx,cy, angle);endif (ccorr>=0.6)mfitbw=(mfit>=1);invbw = xor(mfitbw,ones(size(mfitbw)));source_with_hole = uint8(double(invbw) .* double(imsourcegray));final_image = uint8(double(source_with_hole) + double(mfit));subplot(2,3,5);imshow(final_image); % 显示覆盖了模板脸的灰度图像imsourcegray = final_image;subplot(2,3,6);imshow(Ori_Face); % 显示检测效果图end;if (RectCoord ~= -1)FaceCoord = [FaceCoord; RectCoord];endendendend% 在认为是人脸的区域画矩形[numfaces x] = size(FaceCoord);for i=1:numfaces,hd = rectangle('Position',FaceCoord(i,:));set(hd, 'edgecolor', 'y');end人脸检测是人脸识别、人机交互、智能视觉监控等工作的前提。
用matlab实现人脸识别
用matlab实现人脸识别最近一直在搞这个东西,从一开始什么都不会到现在的能在被人的基础之上改一些代码。
感觉有了不小的进步,现在把这些代码贴出来分享给大家。
先贴一个FLD的完整代码吧!load('orldata.mat');facenumber=length(orldata);for i=1:facenumber%载入人脸库facedatabase{i}=double(orldata{i});endnclass = 40;%类别数nsampleeachclass = 10; %每一类中人脸数neachtrain =4; %每类中选取的用于训练的样本数neachtest = nsampleeachclass-neachtrain; %每类中用于识别的样本数height = 112; %样本的高度width = 92; %样本的宽度for i=1:nclassfor j=1:neachtraingnd((i-1)*neachtrain+j,1)=i;endendfor k=1:20 %随机抽样20次a=rand(1,nsampleeachclass);[a,index]=sort(a);for i=1:nclass %把训练样本与识别样本的每一个点变成一个列向量for j=1:neachtraintrainSample((i-1)*neachtrain+j,:)=reshape(facedatabase{(i-1)* (nsampleeachclass)+index(j)},1,height*width);%reshape函数把图像矩阵转化为行向量;%trainX(:,:,(i-1)*neachtrain+j)=facedatabase{(i-1)*(nsampleea chclass)+index(j)};endfor j=1:neachtesttestSample((i-1)*neachtest+j,:)=reshape(facedatabase{(i-1)*(nsampleeachclass)+index(neachtrain+j)},1 ,height*width);%testX(:,:,(i-1)*neachtest+j)=facedatabase{(i-1)*(nsampleeach class)+index(neachtrain+j)};endendPCAoptions = [];PCAoptions.PCARatio = 0.98;[eigvector_PCA, eigvalue_PCA, meanData, new_X] =PCA(trainSample,PCAoptions);[Wlda, Xlda,r] = LDA1(new_X',gnd, nclass) ;vec=eigvector_PCA*Wlda;[a,b]=size(Wlda);for d=2:2:bnewTrainSample = trainSample*vec(:,1:d);newTestSample = testSample*vec(:,1:d);classification=classif(newTrainSample,newTestSample);suc(k,d/2) = success(classification, neachtrain, neachtest); %每次随机选训练样本对应不同d的成功率clear newTrainSample newTestSample classification;endclear trainSample testSample vec val;endavesuc=mean(suc);disp('Recognition rate:');avesuc其中函数LDA1的代码如下:%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%function [Wlda, Xlda,r] = LDA1( X, XClass, classCount) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%-input X 输入样本按列堆积的矩阵 d*n维% XClass 每一列所属的类别向量% classCount 样本类别总数%-output% Wlda 投影矩阵% Xlda X在Wlda上的投影系数% r 类间散布矩阵Sb的秩,即判别函数的个数???%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%[d,n] = size( X ); % 样本维数d和个数nc = classCount; % 样本的类别数if d < cerror( 'the dimension of training sample must be not less than c!' ); end% 求总体均值及各类样本均值,m = zeros(d,1);m = mean(X,2); % 求总体样本均值,d维列向量XMean = zeros(d,c); % c类样本的均值矩阵for i = 1:ctempMatrix = X(:, find( XClass==i ) ); % 把属于第i类的所有样本储存到tempMatrix中XMean(:,i) = mean( tempMatrix, 2 ); % 计算第i类样本均值,存到XMean第i列end% 求类内散布矩阵SwY=X;for i = 1:nY(:,i) = Y(:,i) - XMean(:,XClass(i)); % 每个样本减去各自所属类的均值endSw = Y * Y.'; % 总类内散布矩阵,d*d维% 求类间散布矩阵SbSb = zeros(d,d);for i = 1:cNi = length( find( XClass == i ) ); % 计算第i类的样本的个数NiSb = Sb + Ni * (XMean(:,i) - m) * (XMean(:,i) - m).'; % 即Sb=N1*(m1-m)*(m1-m)'+...+Nc*(mc-m)*(mc-m)'end% % 也可以利用St=Sb+Sw 如下计算% % St = ( Xpca - kron( ones(1,N), m) ) * ( Xpca - kron( ones(1,N), m) ).'; % % Sb = St - Sw;% 求Sw^-1*Sb的特征值和特征向量% [V,D] = eig(Sw^(-1)*Sb),注意到 [V,D] = EIG(A,B)表示 A*V = B*V*D [V,D] = eig(Sb,Sw); % 即 [V,D] = eig(Sw^(-1)*Sb)Ddiag = diag(D); % 取特征值为列向量Ddiag = Ddiag.'; % 变为行向量[Ddiag, Index] = sort( Ddiag, 'descend' ); % 按降序排列特征值% 求Wlda,Xldar = rank( Sb ); % 求Sb的秩r(r<=c-1),非零的特征值只有r个,只需要求对应的r个特征向量Wlda = zeros( d, r );Xlda = zeros( r, n );Wlda = V(:,Index(1:r)); % 投影矩阵(d*r维)为前r个最大特征值对应的特征向量Wlda = Wlda ./ (ones(size(Wlda, 1), 1) * sqrt(sum(Wlda .^ 2, 1))); % 把投影矩阵的每一列都除以该列的 2-norm(也就是通常的所有元素的平方求和再开根号),即标准化Xlda = Wlda.' * X;。
- 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)。
基于MATLA酌人脸识别源程序1•色彩空间转换function [r,g]=rgb_RGB(Ori_Face)R=0ri_Face(:,:,1);G=0ri_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8 型转换成double型G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;row=size(Ori_Face, 1); %行像素column=size(Ori_Face,2); %列像素for i=1:rowfor j=1:columnrr(i,j)=R1(i,j)/RGB(i,j);gg(i,j)=G1(i,j)/RGB(i,j);endendrrr=mean(rr);r=mean(rrr);ggg=mean(gg);g=mean(ggg); 2•均值和协方差皮肤库\2・jpg');[r2,g2]=rgb_RGB(t2);皮肤库\3・jpg');[r3,g3]=rgb_RGB(t3);皮肤库\4・jpg');[r4,g4]=rgb_RGB(t4);皮肤库\5・jpg');[r5,g5]=rgb_RGB(t5);皮肤库\6・jpg');[r6,g6]=rgb_RGB(t6);皮肤库\7・jpg');[r7,g7]=rgb_RGB(t7);皮肤库\8・jpg');[r8,g8]=rgb_RGB(t8);皮肤库\9・jpg');[r9,g9]=rgb_RGB(t9);皮肤库\10・jpg');[r10,g10]=rgb_RGB(t10); 皮肤库\11・jpg');[r11,g11]=rgb_RGB(t11); 皮肤库\12・jpg');[r12,g12]=rgb_RGB(t12); 皮肤库\13・jpg');[r13,g13]=rgb_RGB(t13); 皮肤库\14・jpg');[r14,g14]=rgb_RGB(t14); 皮肤库\15・jpg');[r15,g15]=rgb_RGB(t15); 皮肤库\16・jpg');[r16,g16]=rgb_RGB(t16); 皮肤库\17・jpg');[r17,g17]=rgb_RGB(t17); 皮肤库\18・jpg');[r18,g18]=rgb_RGB(t18); 皮肤库\19・jpg');[r19,g19]=rgb_RGB(t19); 皮肤库\20・jpg');[r20,g20]=rgb_RGB(t20); 皮肤库\21・jpg');[r21,g21]=rgb_RGB(t21);皮肤库\24・jpg');[r24,g24]=rgb_RGB(t24);皮肤库\25・jpg');[r25,g25]=rgb_RGB(t25);皮肤库\26・jpg');[r26,g26]=rgb_RGB(t26);皮肤库\27・jpg');[r27,g27]=rgb_RGB(t27); r=cat(1,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,r13,r14,r15,r16,r17,r18, r19,r20,r21,r22,r23,r24,r25,r26,r27);g=cat(1,g1,g2,g3,g4,g5,g6,g7,g8,g9,g10,g11,g12,g13,g14,g15,g16,g17,g1 8,g19,g20,g21,g22,g23,g24,g25,g26,g27);m=mean([r,g])n=cov([r,g])3•求质心function [xmean, ymean] = center(bw)bw=bwfill(bw,'holes');area = bwarea(bw);[m n] =size(bw);bw=double(bw);xmean =0; ymean = 0;for i=1:m,for j=1:n,xmean = xmean + j*bw(i,j);ymean = ymean + i*bw(i,j);end;end;if(area==0)xmean=0;ymean=0;elsexmean = xmean/area;ymean = ymean/area;xmean = round(xmean);ymean = round(ymean);end4.求偏转角度function [theta] = orient(bw,xmean,ymean) [m n] =size(bw); bw=double(bw);a = 0;b = 0;c = 0;for i=1:m,for j=1:n,a = a + (j - xmean)A2 * bw(i,j);b = b + (j - xmean) * (i - ymean) * bw(i,j);c = c + (i - ymean)A2 * bw(i,j);end;end;b = 2 * b;theta = atan(b/(a-c))/2;theta = theta*(180/pi); % 从幅度转换到角度5.找区域边界function [left, right, up, down] = bianjie(A)[m n] = size(A);left = -1;right = -1;up = -1;down = -1;for j=1:n,for i=1:m,if (A(i,j) ~= 0)left = j;break;end;end;if (left ~= -1) break;end;end;for j=n:-1:1,for i=1:m,if (A(i,j) ~= 0)right = j;break;end;end;if (right ~= -1) break; end;end;for i=1:m,for j=1:n,if (A(i,j) ~= 0)up = i;break;end;end;if (up ~= -1) break;end;end;for i=m:-1:1,for j=1:n,if (A(i,j) ~= 0)down = i;break;end;end;if (down ~= -1)break;end;end;6.求起始坐标function newcoord = checklimit(coord,maxval)newcoord = coord;if (newcoord<1)newcoord=1;end;if (newcoord>maxval)newcoord=maxval;end;7•模板匹配function [ccorr, mfit, RectCoord]mobanpipei(mult. frontalmodel,ly,wx,cx, cy, angle) frontalmodel=rgb2gray(frontalmodel);model_rot = imresize(frontalmodel,[ly wx],'bilinear'); % 调整模板大小model_rot = imrotate(model_rot,angle,'bilinear'); %旋转模板[l,r,u,d] = bianjie(model_rot); % 求边界坐标bwmodel_rot=imcrop(model_rot,[l u (r-l) (d-u)]); % 选择模板人脸区域[modx,mody] =center(bwmodel_rot); % 求质心[morig, norig] = size(bwmodel_rot);%产生一个覆盖了人脸模板的灰度图像mfit = zeros(size(mult));mfitbw = zeros(size(mult));[limy, limx] = size(mfit);%计算原图像中人脸模板的坐标startx = cx-modx;starty = cy-mody;endx = startx + norig-1;endy = starty + morig-1;startx = checklimit(startx,limx);starty = checklimit(starty,limy);endx = checklimit(endx,limx);endy = checklimit(endy,limy);for i=starty:endy,for j=startx:endx,mfit(i,j) = model_rot(i-starty+1,j-startx+1);end;end;ccorr = corr2(mfit,mult) % 计算相关度[l,r,u,d] = bianjie(bwmodel_rot);sx = startx+l;sy = starty+u;RectCoord = [sx sy (r-1) (d-u)]; % 产生矩形坐标8.主程序clear;[fname,pname]=uigetfile({'*・jpg';'* .bmp';'* ・tif';'* ・gif'},'Please choose a color picture・・・');%返回打开的图片名与图片路径名[u,v]=size(fname);y=fname(v); % 图片格式代表值switch ycase 0errordlg('You Should Load Image File First ・・・','Warning ・・・');case{'g';'G';'p';'P';'f';'F'}; % 图片格式若是JPG/jpg、BMP/bmp、TIF/tif 或者GIF/gif,才打开I=cat(2,pname,fname);Ori_Face=imread(l);subplot(2,3,1),imshow(Ori_Face);otherwiseerrordlg('You Should Load Image File First ・・・','Warning ・・・'); endR=Ori_Face(:,:,1);G=Ori_Face(:,:,2);B=Ori_Face(:,:,3);R1=im2double(R); % 将uint8 型转换成double型处理G1=im2double(G);B1=im2double(B);RGB=R1+G1+B1;m=[ 0・4144,0.3174]; % 均值n=[0・0031,-0・0004;-0・0004,0.0003]; % 方差row=size(Ori_Face,1); % 行像素数column=size(Ori_Face,2); % 列像素数for i=1:rowfor j=1:columnif RGB(i,j)==0rr(i,j)=0;gg(i,j)=0;elserr(i,j)=R1(i,j)/RGB(i,j);% rgb归一化gg(i,j)=G1(i,j)/RGB(i,j);x=[rr(i,j),gg(i,j)];p(i,j)=exp((-0・5)*(x-m)*inv(n)*(x-m)'); % 皮肤概率服从高斯分布endendendsubplot(2,3,2);imshow(p); % 显示皮肤灰度图像low_pass=1/9*ones(3);image_low=filter2(low_pass, p); % 低通滤波去噪声subplot(2,3,3);imshow(image」ow);%自适应阀值程序previousSkin2 = zeros(i,j);changelist =[];for threshold = 0・55:-0.1:0.05two_value = zeros(i,j);two_value(find(image_low>threshold)) = 1;change = sum(sum(two_value - previousSkin2));changelist = [changelist change];previousSkin2 = two_value;end[C, I] = min(changelist);optimalThreshold = (7-1)* 0.1two_value = zeros(i,j);two_value(find(image_low>optimalThreshold))= 1; %二值化subplot(2,3,4);imshow(two_value); % 显示二值图像我的照片人脸模板.jpg'); %读入人脸模板照片FaceCoord=[|;imsourcegray=rgb2gray(Ori_Face); % 将原照片转换为灰度图像[L,N]=bwlabel(two_value,8); % 标注二值图像中连接的部分丄为数据矩阵,N为颗粒的个数for i=1:N,[x,y]=find(bwlabel(two_value)==i); % 寻找矩阵中标号为i 的行和列的下标bwsegment = bwselect(two_value,y,x,8); % 选择出第i 个颗粒numholes = 1-bweuler(bwsegment,4); % 计算此区域的空洞数if (numholes >= 1) % 若此区域至少包含一个洞,则将其选出进行下一步运算RectCoord = -1;[m n] = size(bwsegment);[cx,cy]=center(bwsegment);%求此区域的质心bwnohole=bwfill(bwsegment,'holes'); % 将洞圭寸住(将灰度值赋为1)justface = uint8(double(bwnohole)・* double(imsourcegray));%只在原照片的灰度图像中保留该候选区域angle = orient(bwsegment,cx,cy); %求此区域的偏转角度bw = imrotate(bwsegment, angle, 'bilinear');bw = bwfill(bw,'holes');[l,r,u,d] =bianjie(bw);wx = (r - l +1); % 宽度ly = (d - u + 1); % 高度wratio = ly/wx % 高宽比if ((0 ・8v=wratio)&(wratiov=2))%如果目标区域的高度/宽度比例大于0・8且小于2.0,则将其选出进行下一步运算S=ly*wx; %计算包含此区域矩形的面积A=bwarea(bwsegment); %计算此区域面积if (A/S>0.35)[ccorr,mfit, RectCoord] =mobanpipei(justface,frontalmodel,ly,wx, cx,cy, angle);end if (ccorr>=0.6)mfitbw=(mfit>=1);invbw = xor(mfitbw,ones(size(mfitbw)));source_with_hole = uint8(double(invbw) double(imsourcegray));final_image = uint8(double(source_with_hole) double(mfit));subplot(2,3,5);imshow(final_image); % 显示覆盖了模板脸的灰度图像imsourcegray = final_image;subplot(2,3,6);imshow(Ori_Face); % 显示检测效果图end;if (RectCoord ~= -1)FaceCoord = [FaceCoord; RectCoord];endendendend%在认为是人脸的区域画矩形[numfaces x] = size(FaceCoord);for i=1:numfaces,hd = rectangle('Position',FaceCoord(i,:));set(hd, 'edgecolor', 'y');end人脸检测是人脸识别、人机交互、智能视觉监控等工作的前提。