Human face recognition based on radial basis probabilistic neural network

Author

Guo, Lin ; Huang, De-Shuang

Author_Institution

Inst. of Intelligent Machines, Chinese Acad. of Sci., Hefei, China

Volume

3

fYear

2003

fDate

20-24 July 2003

Firstpage

2208

Abstract

In this paper, a novel human face recognition method based on radial basis probabilistic neural network (RBPNN) is proposed. The orthogonal least square algorithm (OLSA) is used to train the RBPNN and the recursive OLSA is adopted to optimize the structure of the RBPNN. The Olivetti Research Laboratory (ORL) facial database, which is preprocessed by wavelet transformation, is used to test the proposed approach. The experimental results show that the RBPNN achieves higher recognition rate and better classification efficiency with respect to radial basis function neural network (RBFNN) and BP neural network.

Keywords

face recognition; learning (artificial intelligence); least squares approximations; optimisation; radial basis function networks; wavelet transforms; Olivetti research laboratory; human face recognition method; orthogonal least square algorithm; radial basis function neural network; radial basis probabilistic neural network; recursive OLSA; structure optimization; training algorithms; wavelet transformation; Face recognition; Humans; Laboratories; Least squares methods; Machine intelligence; Neural networks; Neurons; Radial basis function networks; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223751

Filename

1223751