Title :
L1-Norm-Based 2DPCA
Author :
Li, Xuelong ; Pang, Yanwei ; Yuan, Yuan
Author_Institution :
State Key Lab. of Transient Opt. & Photonics, Chinese Acad. of Sci., Xi´´an, China
Abstract :
In this paper, we first present a simple but effective L1-norm-based two-dimensional principal component analysis (2DPCA). Traditional L2-norm-based least squares criterion is sensitive to outliers, while the newly proposed L1-norm 2DPCA is robust. Experimental results demonstrate its advantages.
Keywords :
feature extraction; image reconstruction; principal component analysis; L1-norm-based 2DPCA; L2-norm-based least squares criterion; two-dimensional principal component analysis; L1 norm; outlier; subspace; two-dimensional principal component analysis (2DPCA); Algorithms; Artificial Intelligence; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Models, Statistical; Pattern Recognition, Automated; Principal Component Analysis; Reproducibility of Results; Sensitivity and Specificity;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2009.2035629
