Abstract
Linear discriminant analysis (LDA) often encounters small sample size (SSS) problem for high-dimensional data. Null space linear discriminant analysis (NLDA) and linear discriminant analysis based on generalized singular value decomposition (LDA/GSVD) are two popular methods that can solve SSS problem of LDA. In this paper, we present the relation between NLDA and LDA/GSVD under a condition and at the same time propose a modified NLDA (MNLDA) algorithm which has the same discriminating power as LDA/GSVD and is more efficient. In addition, we compare the discriminating capability of NLDA and MNLDA and present our interpretation about this. Experimental results on ORL, FERET, Yale face databases, and the PolyU FKP database support our viewpoints.
Similar content being viewed by others
References
Tenenbaum JB, de Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290:2319–2323
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326
Belkin M, Niyogi P (2003) Laplacian Eigen maps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396
He X, Yan S, Hu Y, Niyogi P, Zhang HJ (2005) Face recognition using Laplacian faces. IEEE Transact Pattern Anal Mach Intell 27(3):328–340
Fu Y, Huang TS (2005) Locally linear embedded Eigen space analysis. University Illinois Urbana-Champaign, Urbana, IL. Technical Report IFP-TR, ECE
Yang J, Zhang D, Yang JY, Niu B (2007) Globally maximizing, locally minimizing: unsupervised discriminant projection with applications to face and palm biometrics. IEEE Transact Pattern Anal Mach Intell 29(4):650–664
Yan S, Xu D, Zhang B, Zhang HJ, Yang Q, Lin S (2007) Graph embedding, extensions: a general framework for dimensionality reduction. IEEE Transact Pattern Anal Mach Intell 29(1):40–51
Chen HT, Chang HW, Liu TL (2005) Local discriminant embedding and its variants, In: Proceedings of CVPR 2005
Fu Y, Liu M, Huang TS (2007) Conformal embedding analysis with local graph modeling on the unit hyper sphere, In: Proceedings of CVPR 2007
Cai D, He X, Zhou K, Han J, Bao H (2007) Locality sensitive discriminant analysis, In: Proceedings of IJCAI
Yang WK, Sun CY, Zhang L (2011) A multi-manifold discriminant analysis method for image feature extraction. Pattern Recogn 44(8):1649–1657
Yang WK, Wang JG, Ren MW, Yang JY, Zhang L, Liu GH (2009) Feature extraction based on Laplacian bidirectional maximum margin criterion. Pattern Recogn 42(11):2327–2334
Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, NY
Belhumeur P, Hespanha J, Kriegman D (1997) Eigen faces versus fisher faces: recognition using class specific linear projection. IEEE Transact Pattern Anal Mach Intell 19(7):711–720
Zuo W, Zhang D, Yang J, Wang K (2006) BDPCA plus LDA: a novel fast feature extraction technique for face recognition. IEEE Transact Syst, Man, Cybern-Part B: Cybern 36(4):946–953
Jing XY, Zhang D, Tang YY (2004) An improved LDA approach. IEEE Transact Syst, Man, Cybern-Part B: Cybern 34(5):1942–1951
Friedman JH (1989) Regularized discriminant analysis. J Am Stat Assoc 84(405):165–175
Chen L-F, Liao H-YM, Ko M-T, Lin J-C, Yu G-J (2000) A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn 33(10):1713–1726
Ye J, Xiong T (2006) Computational and theoretical analysis of null space and orthogonal linear discriminant analysis. J Mach Learn Res 7:1183–1204
Yu H, Yang J (2001) A direct LDA algorithm for high dimensional data with application to face recognition. Pattern Recogn 34(10):2067–2070
Yang J, Yang JY (2003) Why can LDA be performed in PCA transformed space? Pattern Recogn 36(2):563–566
Yang J, Alejandro FF, Yang J, Zhang D, Jin Z (2005) KPCA plus LDA: a complete kernel fisher discriminant framework for feature extraction and recognition. IEEE Transact Pattern Anal Mach Intell 27(2):230–244
Zhuang XS, Dai DQ (2005) Inverse fisher discriminate criteria for small sample size problem and its application to face recognition. Pattern Recogn 38(11):2192–2194
Howland P, Jeon M, Park H (2003) Structure preserving dimension reduction for clustered text data based on the generalized singular value decomposition. SIAM J Matrix Anal Appl 25(1):165–179
Howland P, Park H (2004) Generalizing discriminant analysis using the generalized singular value decomposition. IEEE Transact Pattern Anal Mach Intell 26(8):995–1006
Turk MA, Pentland AP (1991) Face recognition using Eigen faces. In: Proceedings of CVPR 1991
Huang R, Liu Q, Lu H, Ma S (2002) Solving the small sample size problem of LDA. In: Proceedings of ICPR 2002
Paige CC, Saunders MA (1981) Towards a generalized singular value decomposition. SIAM J Num Anal 18(3):398–405
Phillips PJ, Moon H, Rizvi SA, Rauss PJ (2000) The FERET evaluation methodology for face recognition algorithms. IEEE Transact Pattern Anal Mach Intell 22(10):1090–1104
Phillips PJ (2006) The facial recognition technology (FERET) database. http://www.itl.nist.gov/iad/humanid/feret/feret_master.html
Phillips PJ, Wechsler H, Huang J, Rauss P (1998) The FERET database and evaluation procedure for face recognition algorithms. Image Vis Comput 16(5):295–306
Wang X, Tang X (2004) A unified framework for subspace face recognition. IEEE Transact Pattern Anal Mach Intell 26(9):1222–1228
Zhang L, Zhang L, Zhang D, Zhu HL (2010) Online finger-knuckle-print verification for personal authentications. Pattern Recogn 43(7):2560–2571
Acknowledgements
This work is supported by the National Science Foundation of China under Grants No. 60632050, No. 60873151, No. 60973098.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yin, J., Jin, Z. From NLDA to LDA/GSVD: a modified NLDA algorithm. Neural Comput & Applic 21, 1575–1583 (2012). https://doi.org/10.1007/s00521-011-0728-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0728-x