Abstract
Linear Discriminant Analysis (LDA) is a popular feature extraction technique for face recognition. However, it often suffers from the small sample size problem when dealing with the high dimensional face data. Some approaches have been proposed to overcome this problem, but they usually utilize all eigenvectors of null or range subspaces of within-class scatter matrix(S w ). However, experimental results testified that not all the eigenvectors in the full space of are positive to the classification performance, some of which might be negative. As far as we know, there have been no effective ways to determine which eigenvectors in full space should be adopted. This paper proposes a new method EDA+Full-space LDA, which takes full advantage of the discriminative information of the null and range subspaces of by selecting an optimal subset of eignvectors. An Estimation of Distribution Algorithm (EDA) is used to pursuit a subset of eigenvectors with significant discriminative information in full space of . EDA+Full-space LDA is tested on ORL face image database. Experimental results show that our method outperforms other LDA methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Fukunaga, K.: Introduction to statistical pattern recognition, 2nd edn. Academic Press, Boston (1990)
Yu, H., Yang, J.: A direct lda algorithm for high-dimensional data with application to face recognition. Pattern Recognition 34(10), 2067–2070 (2001)
Chen, L., Liao, H., Ko, M., Lin, J., Yu, G.: A new lda-based face recognition system which can solve the samll sample size problem. Pattern Recognition 33(10), 1713–1726 (2000)
Yang, J., Yang, J.: Optimal FLD algorithm for facial feature extraction. SPIE Proceedings of the Intelligent Robots and Computer Vision XX: Algorithms,Techniques, and Active Vision 4572, 438–444 (2001)
Wang, X., Tang, X.: Dual-space Linear Discrminant Analysis for Face Recognition. In: Proceeding of Computer Vision and Pattern Recognition, vol. 2, pp. 564–569 (2004)
Belhumeur, P.N., Hespanha, J., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 711–720 (1997)
Thomaz, C.E., Gillies, D.F.: A Maximum Uncertainty LDA-Based Approach for Limited Sample Size Problems - With Application to Face Recognition. In: Proceeding of Computer Graphics and Image Processing, SIBGRAPI 2005, pp. 89–96. IEEE CS Press, New York (2005)
Larranaga, P., Lozano, J.A.: Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation. Kluwer Academic Publishers, New York (2001)
Saeys, Y., Degroeve, S., Aeyels, D., Van de Peer, Y., Rouz, P.: Fast feature selection using a simple Estimation of Distribution Algorithm: A case study on splice site prediction. Bioinformatics 19, II179–II188 (2003)
Muhlenbein, H.: The equation for response to selection and its use for prediction. Evolutionary Computation 5, 303–346 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, X., Li, B., Chen, H., Wang, X., Zhuang, Z. (2007). Full-Space LDA With Evolutionary Selection for Face Recognition. In: Wang, Y., Cheung, Ym., Liu, H. (eds) Computational Intelligence and Security. CIS 2006. Lecture Notes in Computer Science(), vol 4456. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74377-4_115
Download citation
DOI: https://doi.org/10.1007/978-3-540-74377-4_115
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74376-7
Online ISBN: 978-3-540-74377-4
eBook Packages: Computer ScienceComputer Science (R0)