×

Regularized discriminant analysis and its application to face recognition. (English) Zbl 1032.68129

Summary: We propose a new regularization scheme to overcome the small sample size problem in the linear discriminant analysis. A regularized discriminant analysis algorithm is developed and applied to face recognition. Experimental results show that heavy weights should be added to the between-class covariance matrix for regularization. The experimental results of the proposed regularized discriminant analysis algorithm on Yale and Olivetti databases are encouraging.

MSC:

68T10 Pattern recognition, speech recognition
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chen, L.; Liao, H.; Ko, M.; Lin, J.; Yu, G., A new LDA-based face recognition system which can solve the small sample size problem, Pattern Recognition, 33, 10, 1713-1726 (2000)
[2] Liu, K.; Cheng, Y.; Yang, J., Algebraic feature extraction for image recognition based on an optimal discriminant criterion, Pattern Recognition, 26, 6, 903-911 (1993)
[3] Yu, H.; Yang, J., A direct LDA algorithm for high-dimensional data—with application to face recognition, Pattern Recognition, 34, 2067-2070 (2001) · Zbl 0993.68091
[4] W. Zhao, R. Chellappa, P.J. Phillips, Subspace linear discriminant analysis for face recognition, Technical Report CAR-TR-914, CS-TR-4009, University of Maryland at College Park, USA, 1999, IEEE Trans. Image Processing, 2001, submitted for publication.; W. Zhao, R. Chellappa, P.J. Phillips, Subspace linear discriminant analysis for face recognition, Technical Report CAR-TR-914, CS-TR-4009, University of Maryland at College Park, USA, 1999, IEEE Trans. Image Processing, 2001, submitted for publication.
[5] Belhumeur, P. N.; Hespanha, J. P.; Kriegman, D. J., Eigenfaces vs. Fisherfaces: recognition using class specific linear projection, IEEE Trans. Pattern Anal. Mach. Intell., 19, 7, 711-720 (1997)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.