readme.1st

来自「PCA MATLAB源代码」· 1ST 代码 · 共 74 行

_________________________________________________

 PCA Face Recognition

 MatLab implementation 

http://www.vision.ime.usp.br/~teo/pca
_________________________________________________

Instructions:

1 - Open file pca.m.

2 - Read its comments and replace the "???"
    to the parameters that you have to set
    (location of face image database,
    number of eigenfaces, etc).

3 - Script pca.m uses the functions resize.m, 
    loadpop.m, makebasis.m, classif.m and 
    success.m. You can learn a little bit
    about them by reading the script pca.m.

4 - The purpose of function showimg.m is to
    plot the images. Function pca.m does not
    call it.

5 - All the functions have descriptions and
    you can see them by typing 
    "help <function_name>" in the MatLab's 
    command line.

6 - For the face image database, I recommended 
    that: 
    * your image database contains only the 
      images that you will use for training 
      and testing the PCA face recognition 
      system; 
    * all the people have the same number of
      images in the database;
    * the file names be like xxx_yyy, where
      xxx is the number of the person of this
      file and yyy is the number of this sample
      image of that person.

7 - After setting the correct paramethers
    in the script pca.m, you can run it and
    it will perform the training of a PCA
    system and a recognition process.


I hope you enjoy it!

If you have any problem, suggestion, comments 
or if you improved this version, please contact me.

_____________________________________________

Credits:

 Teofilo Emidio de Campos

 mailto:[e-mail]
 http://www.ime.usp.br/~teo
 ICQ# 6011445
 Creative Vision Research Group
 http://www.ime.usp.br/~cesar/creativision
 Computer Science Department
 Institute of Mathematics and Statistics
 Sao Paulo University - Brazil
 DCC - IME - USP

 Last update: Wed May 17  2000