Face recognition by using neural network classifiers based on PCA and LDA

Author

Oh, Byung-Joo

Author_Institution

Dept. of Electron. Eng., Hannam Univ., Daejeon, South Korea

Volume

2

fYear

2005

fDate

10-12 Oct. 2005

Firstpage

1699

Abstract

This paper proposes a face recognition method using neural network classifiers based on principal component analysis (PCA) and linear discriminant analysis (LDA). The PCA or LDA features of the face images are then classified by the multiple layer neural network (MLNN) or radial basis function (RBF) network. The proposed approach has been tested on the ORL database. The experimental results have been demonstrated that the performance of PCA+MLNN is superior to that of the LDA+RBFN.

Keywords

face recognition; multilayer perceptrons; pattern classification; principal component analysis; radial basis function networks; ORL database; face recognition; linear discriminant analysis; multiple layer neural network; neural network classifiers; principal component analysis; radial basis function network; Face recognition; Function approximation; Image databases; Linear discriminant analysis; Multi-layer neural network; Neural networks; Principal component analysis; Radial basis function networks; Testing; Vectors; Principal component analysis; error back-propagation; face recognition; linear discrimination analysis; radial basis function network.;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2005 IEEE International Conference on

Print_ISBN

0-7803-9298-1

Type

conf

DOI

10.1109/ICSMC.2005.1571393

Filename

1571393