2DPCA 两维的主成分分析法人脸识别

clear all clc close all %选择训练样本路径 TrainDatabasePath = uigetdir('E:\VOA\ORL', 'Select training database path' ); %选择测试样本路径 TestDatabasePath = uigetdir('E:\VOA\ORL', 'Select test database path'); c1=clock; %生成测试数据集 %T = CreateDatabase(TrainDatabasePath); TrainFiles = dir(TrainDatabasePath); class_Number = 0; s=size(TrainFiles,1); %计算训练样本个数 for i = 1:size(TrainFiles,1) if not(strcmp(TrainFiles(i).name,'.')|strcmp(TrainFiles(i).name,'..')|strcmp(TrainFiles(i).name,'README')) class_Number = class_Number + 1; % Number of all images in the training database end end %读取训练集第一个图像，得到其尺寸，初始化图像矩阵 str = strcat(TrainDatabasePath,'\s1.\1.jpg'); img = imread(str); [irow,icol] = size(img); A=zeros(irow,icol,2); %合计有Train_Number人的目录，每个目录存放某人的10幅人脸图像,取前n副图像做训练样本 n=str2double(inputdlg('please input NumImaTra(must be int number)','INPUT NumImaTra',1,{'5'}));%训练样本下面读入人脸图像，共四十人，每人十幅图像，图像大小为112*92 d=str2double(inputdlg('please input Characteristic dimension(must be int number)','INPUT Characteristic dimension',1,{'2'})); for i = 1 : class_Number topdir = int2str(i); topdir = strcat(TestDatabasePath,'\s',topdir); for j= 1 : n %for j= 1 :2 :9 str = int2str(j); str = strcat(topdir,'\',str,'.jpg'); img = imread(str); A(:,:,n*(i-1)+j) = img; end end %得到训练样本的个数Train_Number Train_Number = size(A,3); %求所有训练样本向量的均值 M M=mean(A,3); %求图像散布矩阵Gt Gt=zeros(icol,icol); for i = 1 : Train_Number temp = A(:,:,i)-M; Gt = Gt + temp'*temp; end Gt=Gt/Train_Number; [V D] = eigs(Gt,d); %ＰＣＡ空间投影图像 %V = orth(V); ProjectedImages = zeros(irow,d); for i = 1 : Train_Number ProjectedImages(:,:,i) = A(:,:,i)*V; end c2=clock; fprintf('特征抽取时间:');etime(c2,c1) %特征抽取时间 %已识别测试集的数目Recnum c3=clock; Recnum=0; for i = 1 : class_Number topdir = int2str(i); topdir = strcat(TestDatabasePath,'\s',topdir); for j= n+1:10 %for j= 2 :2 :10 str = int2str(j); TestImage = strcat(topdir,'\',str,'.jpg'); %测试样本路径 %测试样本原始数据 im = imread(TestImage); %测试样本的投影 ProjectedTestImage = double(im)*V; gc=[]; % for t=1 : class_Number %mk=mean( ProjectedImages( :,:,(t-1)*n+1:t*n), 3); %此处参数t*n，n是前n个样本作为训练样本， %temp = norm( ProjectedTestImage - mk ); %gc=[gc temp]; % end for i=1 : Train_Number temp = norm( ProjectedTestImage - ProjectedImages( :,:,i ),'fro'); gc=[gc temp]; end [dist_min , Recognized_index1] = min(gc); Recognized_index1 = floor((Recognized_index1-1)/n)+1; OutputName = Recognized_index1; OutputName =strcat(TestDatabasePath,'\s',int2str(OutputName)); %如果测试样本分类正确，则 Recnum加1 if(strcmp(OutputName,topdir)==1) Recnum = Recnum+1; end %返回测试样本和其所匹配的样本信息 %disp(TestImage); Recognized_index1 = strcat('Matched image No is : ',int2str(Recognized_index1)) ; %disp( Recognized_index1 ); str = strcat('Matched image is : ',OutputName); % disp(str); end end str=strcat('recognition count : ', int2str(Recnum)); disp(str ); str=strcat('recognition rate:',num2str(Recnum/(class_Number*(10-n)))); disp(str); c4=clock; fprintf('识别时间:');etime(c4,c3) %识别时间