Title :
A comparison between two preprocessing techniques in PCA-based face recognition
Author :
Ciocoiu, Iulian B. ; Valmar, B.
Abstract :
We present a comparative analysis of the recognition performances of 2 different preprocessing techniques for face recognition application. The specific methods are projection-combined principal component analysis ((PC)2A) and eigenhills, which are compared against standard eigenface method. Recognition performances are computed using different distance measures and number of training images on the Olivetti database.
Keywords :
eigenvalues and eigenfunctions; face recognition; principal component analysis; Olivetti database; PCA-based face recognition; distance measures; eigenface method; face recognition application; preprocessing techniques; projection-combined principal component analysis; recognition performances; training images;
Conference_Titel :
Signals, Circuits and Systems, 2003. SCS 2003. International Symposium on
Print_ISBN :
0-7803-7979-9
DOI :
10.1109/SCS.2003.1227004
