Nuclear Norm Based 2DPCA

Author

Fanlong Zhang ; Jianjun Qian ; Jian Yang

Author_Institution

Sch. of Comput. Sci. & Technol., Nanjing Univ. of Sci. & Technol., Nanjing, China

fYear

2013

Firstpage

74

Lastpage

78

Abstract

This paper presents a novel method, namely nuclear norm based 2DPCA (N-2DPCA), for image feature extraction. Unlike the conventional 2DPCA, N-2DPCA uses a nuclear norm based reconstruction error criterion. The criterion is minimized by converting the nuclear norm based optimization problem into a series of F-norm based optimization problems. N-2DPCA is applied to face recognition and is evaluated using the Extended Yale B and CMU PIE databases. Experimental results demonstrate that our method is more effective and robust than PCA, 2DPCA and L1-Norm based 2DPCA.

Keywords

face recognition; matrix algebra; principal component analysis; CMU PIE database; Extended Yale B database; F-norm based optimization problems; L1-norm based 2DPCA; PCA; face recognition; nuclear norm based 2DPCA; nuclear norm based reconstruction error criterion; two-dimensional principal component analysis; Databases; Lighting; Linear programming; Optimization; Principal component analysis; Testing; Training; feature extraction; nuclear norm; principal component analysis; subspace analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ACPR), 2013 2nd IAPR Asian Conference on

Conference_Location

Naha

Type

conf

DOI

10.1109/ACPR.2013.10

Filename

6778285