Comparison of eigenface-based feature vectors under different impairments

Author

Pnevmatikakis, Aristodemos ; Polymenakos, Lazaros

Author_Institution

Autonomic Comput. Lab., Athens Inf. Technol. Inst., Greece

Volume

1

fYear

2004

fDate

23-26 Aug. 2004

Firstpage

296

Abstract

We study the performance of a new eigenface-based method for face recognition. Specifically, we perform DCT preprocessing followed by the PCA-LDA combination. We compare the new method to existing ones (PCA, PCA-LDA, DCT-PCA) under impairments like changes in brightness, direction-of-illumination, hairstyle, clothing, expression, head orientation, and added noise. In this paper feature extraction methods are outlined. The results are obtained using two different face databases: the Aberdeen database from University of Stirling and the ORL database from University of Cambridge.

Keywords

discrete cosine transforms; eigenvalues and eigenfunctions; face recognition; feature extraction; principal component analysis; visual databases; Aberdeen database; DCT; Olivetti research laboratory database; PCA-LDA combination; University of Cambridge; University of Stirling; brightness; direction of illumination; eigenface based feature vector; face databases; face recognition; feature extraction methods; linear discriminant analysis; Clothing; Discrete cosine transforms; Face recognition; Feature extraction; Head; Noise robustness; Principal component analysis; Scattering; Spatial databases; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-2128-2

Type

conf

DOI

10.1109/ICPR.2004.1334111

Filename

1334111