Face Recognition System Based on EigenFaces Method

Only available on StudyMode
  • Topic: Eigenface, Facial recognition system, Eigenvalue, eigenvector and eigenspace
  • Pages : 12 (1958 words )
  • Download(s) : 160
  • Published : May 24, 2013
Open Document
Text Preview
% Face recognition system based on EigenFaces Method.
% The system functions by projecting face images onto a feature space % that spans the significant variations among known face images. The % significant features are known as "eigenfaces" because they are the % eigenvectors (principal components) of the set of faces.

% Face images must be collected into sets: every set (called "class") should % include a number of images for each person, with some variations in  % expression and in the lighting. When a new input image is read and added % to the training database, the number of class is required. Otherwise, a new  % input image can be processed and confronted with all classes present in database. % We choose a number of eigenvectors M' equal to the number of classes (see  % algorithmic details in the cited references). Before starting image % processing first select input image. This image can be successively added to % database (training) or, if a database is already present, matched with % known faces.

% The images included are taken from AT&T Laboratories Cambridge's % Face DataBase. See the cited references for more informations. % 

% Select image:                                  read the input image %
% Add selected image to database:                the input image is added to database and will be used for training %
% Database Info:                                 show informations about the images present in database. Images must  %                                                have the same size. If this is not true you have to resize them. %

% Face Recognition:                              face matching. The selected input image is processed  %
% Delete Database:                               remove database from the current directory %
% Info:                                          show informations about this software %
% Visualization tool:                            visualization utility %
% Source code for Face Recognition System:       how to obtain the complete source code %
% Exit:                                          quit program %
%  References:
%  "Eigenfaces for Recognition", Matthew Turk and Alex Pentlad %  Journal of Cognitive Neuroscience pp.71-86, March 1991
%  Vision and Modeling Group, The Media Laboratory
%  Massachusetts Institute of Technology.
%  This paper is available at http://www.cs.ucsb.edu/~mturk/Papers/jcn.pdf %  See also Matthew Turk's homepage http://www.cs.ucsb.edu/~mturk/research.htm %
%  AT&T Laboratories Cambridge. The ORL face database, Olivetti Research Laboratory available at %  http://www.uk.research.att.com/pub/data/att_faces.zip
%  or http://www.uk.research.att.com/pub/data/att_faces.tar.Z %
%-------------------------------------------------------------------- clear;

messaggio='Insert the number of set: each set determins a class. This set should include a number of images for each person, with some variations in expression and in the lighting.';

while chos~=possibility,
    chos=menu('Face Recognition System','Select image','Add selected image to database','Database Info','Face Recognition','Delete Database','Info',...         'Visualization tool','Source code for Face Recognition System','Exit');     %----------------

    if chos==1,
        [namefile,pathname]=uigetfile('*.*','Select image');         if namefile~=0
            [img,map]=imread(strcat(pathname,namefile));             imshow(img);
            dimensioni = size(img);
            disp('Input image has been selected.');             disp('Now press on "Add selected image to database" button to add this image to database or,');             disp('press on "Face Recognition" button to start face matching.');         else

            warndlg('Input image must be selected.',' Warning ')         end
    if chos==2,...
tracking img