Block Principal Component Analysis With Nongreedy $\ell _{1}$ -Norm Maximization

Block principal component analysis with ℓ1-norm (BPCA-L1) has demonstrated its effectiveness in a lot of visual classification and data mining tasks. However, the greedy strategy for solving the ℓ1-norm maximization problem is prone to being struck in local solutions. In this paper, we propose a BPCA with nongreedy ℓ1-norm maximization, which obtains better solutions than BPCA-L1 with all the projection directions optimized simultaneously. Other than BPCA-L1, the new algorithm has been evaluated against some popular principal component analysis (PCA) algorithms including PCA-L1 and 2-D PCA-L1 on a variety of benchmark data sets. The results demonstrate the effectiveness of the proposed method.

[1]  Xuelong Li,et al.  Multiresolution Imaging , 2014, IEEE Transactions on Cybernetics.

[2]  Quanxue Gao,et al.  Is two-dimensional PCA equivalent to a special case of modular PCA? , 2007, Pattern Recognit. Lett..

[3]  Daming Shi,et al.  TPSLVM: A Dimensionality Reduction Algorithm Based On Thin Plate Splines , 2014, IEEE Transactions on Cybernetics.

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

[5]  Xuelong Li,et al.  Data Uncertainty in Face Recognition , 2014, IEEE Transactions on Cybernetics.

[6]  Jian Yang,et al.  Integrating Conventional and Inverse Representation for Face Recognition , 2014, IEEE Transactions on Cybernetics.

[7]  Vijayan K. Asari,et al.  An improved face recognition technique based on modular PCA approach , 2004, Pattern Recognit. Lett..

[8]  Rong Wang,et al.  Robust 2DPCA With Non-greedy $\ell _{1}$ -Norm Maximization for Image Analysis , 2015, IEEE Transactions on Cybernetics.

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

[10]  Jing Wang,et al.  Robust Face Recognition via Adaptive Sparse Representation , 2014, IEEE Transactions on Cybernetics.

[11]  Haixian Wang,et al.  Block principal component analysis with L1-norm for image analysis , 2012, Pattern Recognit. Lett..

[12]  Ivor W. Tsang,et al.  Flexible Manifold Embedding: A Framework for Semi-Supervised and Unsupervised Dimension Reduction , 2010, IEEE Transactions on Image Processing.

[13]  Jiawei Han,et al.  Orthogonal Laplacianfaces for Face Recognition , 2006, IEEE Transactions on Image Processing.

[14]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  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).

[16]  Yao Zhao,et al.  Topographic NMF for Data Representation , 2014, IEEE Transactions on Cybernetics.

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

[18]  Feiping Nie,et al.  Robust Principal Component Analysis with Non-Greedy l1-Norm Maximization , 2011, IJCAI.

[19]  Chong-Ho Choi,et al.  Image covariance-based subspace method for face recognition , 2007, Pattern Recognit..

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

[21]  Hongyuan Zha,et al.  {\it R}$_{\mbox{1}}$-PCA: rotational invariant {\it L}$_{\mbox{1}}$-norm principal component analysis for robust subspace factorization , 2006, ICML 2006.