A principal component based probabilistic DBNN for face recognition

Author

Shen, L.J. ; Fu, H.C. ; Xu, Y.Y. ; Hsu, F.R. ; Chang, H.T. ; Meng, W.Y.

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan

Volume

3

fYear

1996

fDate

16-19 Sep 1996

Firstpage

499

Abstract

Principal component analysis (PCA) is a powerful statistical approach for extracting facial features for recognition. The eigenface method has been reported to provide significant recognition performance over various testing and evaluation procedures. We try to improve the PCA recognition performance by concatenating a probabilistic decision based neural networks (DBNN). Our experiments show that the hybrid PCA/NN systems can improve the recognition rate by about 8% better than the PCA systems, on our facial database, which contains large rotation face images as the testing sets

Keywords

eigenvalues and eigenfunctions; face recognition; feature extraction; neural nets; probability; statistical analysis; eigenface method; experiments; face recognition; facial database; facial feature extraction; principal component analysis; probabilistic decision based neural networks; recognition performance; recognition rate; statistical approach; testing sets; Application software; Computer science; Contracts; Face recognition; Image databases; Image recognition; Neural networks; Power engineering and energy; Principal component analysis; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1996. Proceedings., International Conference on

Conference_Location

Lausanne

Print_ISBN

0-7803-3259-8

Type

conf

DOI

10.1109/ICIP.1996.560540

Filename

560540