基于PCA人脸识算法代码

1一种基于图象分析的柜员机 -人脸识别算法的研究代码1.EigenfaceCode.m：function m, A, Eigenfaces = EigenfaceCore(T)% Use Principle Component Analysis (PCA) to determine the most % discriminating features between images of faces.% Description: This function gets a 2D matrix, containing all training image vectors% and returns 3 outputs which are extracted from training database.% Argument: T - A 2D matrix, containing all 1D image vectors.% Suppose all P images in the training database % have the same size of MxN. So the length of 1D % column vectors is M*N and T will be a MNxP 2D matrix.% % Returns: m - (M*Nx1) Mean of the training database% Eigenfaces - (M*Nx(P-1) Eigen vectors of the covariance matrix of the training database% A - (M*NxP) Matrix of centered image vectors% See also: EIG% Original version by Amir Hossein Omidvarnia, October 2007% Email: aomidvarece.ut.ac.ir % Calculating the mean image m = mean(T,2); % Computing the average face image m = (1/P)*sum(Tjs) (j = 1 : P)Train_Number = size(T,2);2% Calculating the deviation of each image from mean imageA = ; for i = 1 : Train_Numbertemp = double(T(:,i) - m; % Computing the difference image for each image in the training set Ai = Ti - mA = A temp; % Merging all centered imagesend% Snapshot method of Eigenface methos% We know from linear algebra theory that for a PxQ matrix, the maximum% number of non-zero eigenvalues that the matrix can have is min(P-1,Q-1).% Since the number of training images (P) is usually less than the number% of pixels (M*N), the most non-zero eigenvalues that can be found are equal% to P-1. So we can calculate eigenvalues of A*A (a PxP matrix) instead of% A*A (a M*NxM*N matrix). It is clear that the dimensions of A*A is much% larger that A*A. So the dimensionality will decrease.L = A*A; % L is the surrogate of covariance matrix C=A*A.V D = eig(L); % Diagonal elements of D are the eigenvalues for both L=A*A and C=A*A.% Sorting and eliminating eigenvalues% All eigenvalues of matrix L are sorted and those who are less than a% specified threshold, are eliminated. So the number of non-zero% eigenvectors may be less than (P-1).3L_eig_vec = ;for i = 1 : size(V,2) if( D(i,i)1 )L_eig_vec = L_eig_vec V(:,i);endend% Calculating the eigenvectors of covariance matrix C% Eigenvectors of covariance matrix C (or so-called “Eigenfaces“)% can be recovered from Ls eiegnvectors.Eigenfaces = A * L_eig_vec; % A: centered image vectors42.pcafacesys.m:function varargout = pcafacesys(varargin)% PCAFACESYS M-file for pcafacesys.fig% PCAFACESYS, by itself, creates a new PCAFACESYS or raises the existing% singleton*.% H = PCAFACESYS returns the handle to a new PCAFACESYS or the handle to% the existing singleton*.% PCAFACESYS(CALLBACK,hObject,eventData,handles,.) calls the local% function named CALLBACK in PCAFACESYS.M with the given input arguments.% PCAFACESYS(Property,Value,.) creates a new PCAFACESYS or raises the% existing singleton*. Starting from the left, property value pairs are% applied to the GUI before pcafacesys_OpeningFcn gets called. An% unrecognized property name or invalid value makes property application% stop. All inputs are passed to pcafacesys_OpeningFcn via varargin.% *See GUI Options on GUIDEs Tools menu. Choose “GUI allows only one% instance to run (singleton)“.5% See also: GUIDE, GUIDATA, GUIHANDLES% Edit the above text to modify the response to help pcafacesys% Last Modified by GUIDE v2.5 03-May-2017 01:41:51% Begin initialization code - DO NOT EDITgui_Singleton = 1;gui_State = struct(gui_Name, mfilename, .gui_Singleton, gui_Singleton, .gui_OpeningFcn, pcafacesys_OpeningFcn, .gui_OutputFcn, pcafacesys_OutputFcn, .gui_LayoutFcn, , .gui_Callback, );if nargin endif nargoutvarargout1:nargout = gui_mainfcn(gui_State, varargin:);elsegui_mainfcn(gui_State, varargin:);end% End initialization code - DO NOT EDIT% - Executes just before pcafacesys is made visible.function pcafacesys_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 pcafacesys (see VARARGIN)% Choose default command line output for pcafacesys6handles.output = hObject;% Update handles structureguidata(hObject, handles);% UIWAIT makes pcafacesys wait for user response (see UIRESUME)% uiwait(handles.figure1);% - Outputs from this function are returned to the command line.function varargout = pcafacesys_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 structurevarargout1 = handles.output;% - Executes on button press in load_btn.function load_btn_Callback(hObject, eventdata, handles)% hObject handle to load_btn (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA)global filename; %全局变量，文件名称global pname; %全局变量，文件路径global fname; %全局变量，文件名字global info; %全局变量，表示 avi 文件的信息global videodata; %全局变量，表示视频信息的数据global mov;global nowpic;global saveindex;global faceindex;faceindex=1;saveindex=1;%初始化人脸识别界面7h = waitbar(0.1,检测硬件，请等待.);global vidvid = videoinput(winvideo,1);vid_src=getselectedsource(vid);data = getsnapshot(vid);waitbar(0.5,h,初始化窗口，请等待.);set(vid,TriggerRepeat,Inf);set(vid,FramesPerTrigger,1);set(vid,FrameGrabInterval,1);vidRes = get(vid, VideoResolution);nBands = get(vid, NumberOfBands);% % % axes(handles.axes1);% Display the video data in your GUI.waitbar(1.0,h,初始化窗口，请等待.);close(h);% % % hImage = image( zeros(vidRes(2), vidRes(1), nBands) );% % % % % axes(handles.src_axes);% % % preview(vid, hImage);hImage=image(zeros(vidRes(2), vidRes(1), nBands);preview(vid,hImage);% - Executes on button press in pushbutton3.function pushbutton3_Callback(hObject, eventdata, handles)% hObject handle to pushbutton3 (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA)global m;global A;global Eigenfaces;global croppic;global trainpic;global namecode;8global train_Y;global vector;global C;global gamma;global multiSVMStruct;global mov;global nowpic;global namecode; global M;global Train_Number;global ProjectedImages;global trainpicture;temp = rgb2gray(croppic);resizepic=imresize(temp,300,200);temp=resizepic;%测试图像和训练图像，差距 a b = size(temp); InImage = reshape(temp,a*b,1);%将读取的测试图像 temp reshape 为只有 一 列 的矩阵 InImage Difference = double(InImage)-M; % Centered test image 将测试图像和 m 作差，m 在前面讲述过，为所有图像灰度 reshape 后矩阵的平均值矩阵 ProjectedTestImage = Eigenfaces*Difference; % 特征脸和 differece 相乘得到 投影的 测试 图像 %测试图像特征向量 %differece 是只有 1 列的矩阵，特征脸是 N 列 N 行的矩阵,相乘得到只有 1 列的 ProjectedTestImage 矩阵 %识别过程，得到最后的识别图 Euc_dist = ; for i = 1 : Train_Number 9q = ProjectedImages(:,i); %表示该投影的图像矩阵 第 i 列 的所有元素，定义为 q temp = ( norm( ProjectedTestImage - q ) )2; %只有 1 列的ProjectedTestImage 矩阵与投影的图像矩阵 第 i 列作差，平方，得矩阵 temp %算法Euc_dist = Euc_dist temp; % 合并为 Euc_dist 矩阵 end Euc_dist_min , Recognized_index = min(Euc_dist);%取得 Euc_dist 矩阵最小值 Euc_dist_min %Recognized_index 为对应的第几个 % % % p= int2str(Recognized_index) % % % OutputName = strcat(pic,p,.bmp); A=resizepic; B=trainpictureRecognized_index;A=A-mean2(A);B=B-mean2(B); similar = sum(sum(A.*B)/sqrt(sum(sum(A.*A)*sum(sum(B.*B);%相似度算法，similar 为最后的相似度值 if similar0.8 set(handles.result_edit,string,不是本人 );%clear();elseset(handles.result_edit,string,本人 );%clear();endfunction result_edit_Callback(hObject, eventdata, handles)% hObject handle to result_edit (see GCBO)% eventdata reserved - to be defined in a future version of MATLAB% handles structure with handles and user data (see GUIDATA)10% Hints: get(hObject,String) returns contents of result_edit as text% str2double(get(hObj