Generalized 2-D Principal Component Analysis by Lp-Norm for Image Analysis

This paper proposes a generalized 2-D principal component analysis (G2DPCA) by replacing the L2-norm in conventional 2-D principal component analysis (2DPCA) with Lp-norm, both in objective and constraint functions. It is a generalization of previously proposed robust or sparse 2DPCA algorithms. Under the framework of minorization-maximization, we design an iterative algorithm to solve the optimization problem of G2DPCA. A closed-form solution could be obtained in each iteration. Then a deflating scheme is employed to generate multiple projection vectors. Our algorithm guarantees to find a locally optimal solution for G2DPCA. The effectiveness of the proposed method is experimentally verified.

[1]  Jiashu Zhang,et al.  Linear Discriminant Analysis Based on L1-Norm Maximization , 2013, IEEE Transactions on Image Processing.

[2]  Lester W. Mackey,et al.  Deflation Methods for Sparse PCA , 2008, NIPS.

[3]  Takeo Kanade,et al.  Robust L/sub 1/ norm factorization in the presence of outliers and missing data by alternative convex programming , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Yurii Nesterov,et al.  Generalized Power Method for Sparse Principal Component Analysis , 2008, J. Mach. Learn. Res..

[5]  D. Hunter,et al.  Optimization Transfer Using Surrogate Objective Functions , 2000 .

[6]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[7]  Rafael Martí.  Multi-Start Methods , 2003, Handbook of Metaheuristics.

[8]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[9]  David Zhang,et al.  A Generalized Iterated Shrinkage Algorithm for Non-convex Sparse Coding , 2013, 2013 IEEE International Conference on Computer Vision.

[10]  Nojun Kwak,et al.  Principal Component Analysis Based on L1-Norm Maximization , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Michael I. Jordan,et al.  A Direct Formulation for Sparse Pca Using Semidefinite Programming , 2004, NIPS 2004.

[12]  Deyu Meng,et al.  Improve robustness of sparse PCA by L1-norm maximization , 2012, Pattern Recognit..

[13]  Nojun Kwak,et al.  Principal Component Analysis by $L_{p}$ -Norm Maximization , 2014, IEEE Transactions on Cybernetics.

[14]  Ern G Kwon,et al.  On a generalized Hölder inequality , 2015 .

[15]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[16]  R. Tibshirani,et al.  A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. , 2009, Biostatistics.

[17]  D. Hunter,et al.  A Tutorial on MM Algorithms , 2004 .

[18]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[19]  Jiashu Zhang,et al.  Discriminant Locality Preserving Projections Based on L1-Norm Maximization , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Xuelong Li,et al.  L1-Norm-Based 2DPCA , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[22]  R. Tibshirani,et al.  Sparse Principal Component Analysis , 2006 .

[23]  Jianhua Z. Huang,et al.  Sparse principal component analysis via regularized low rank matrix approximation , 2008 .

[24]  Lawrence Carin,et al.  Sparse multinomial logistic regression: fast algorithms and generalization bounds , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  WEI H. YANG,et al.  On generalized Ho¨der inequality , 1991 .

[26]  Chris H. Q. Ding,et al.  R1-PCA: rotational invariant L1-norm principal component analysis for robust subspace factorization , 2006, ICML.

[27]  Jing Wang,et al.  2DPCA with L1-norm for simultaneously robust and sparse modelling , 2013, Neural Networks.

[28]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[30]  Paul S. Bradley,et al.  Feature Selection via Concave Minimization and Support Vector Machines , 1998, ICML.

[31]  Youfu Li,et al.  Feature extraction based on Lp-norm generalized principal component analysis , 2013, Pattern Recognit. Lett..

[32]  Xuesong Lu,et al.  Fisher Discriminant Analysis With L1-Norm , 2014, IEEE Transactions on Cybernetics.