Share Email Print

Journal of Electronic Imaging

Joint sparsity matrix learning for multiclass classification applied to face recognition
Author(s): Minna Qiu; Zhengming Li; Hongzhi Zhang; Charlene Xie; Jian Zhang
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Multiclass classification is an important problem in pattern recognition. Various classification methods have been proposed in the past few decades. However, most of these classification methods neglect the errors or the noises that exist in samples. As a result, classification accuracy is badly influenced by the errors or noises. In this paper, we propose a joint sparsity matrix learning method, which exploits l 2,1 -norm minimization to perform multiclass classification. In order to overcome the influence of the errors or noises, we introduce a sparse matrix to explicitly model the errors or noises and apply an iterative procedure to solve the l 2,1 -norm regularized problem. We perform experiments on four face databases to verify the effectiveness of the proposed method.

Paper Details

Date Published: 19 May 2014
PDF: 9 pages
J. Electron. Imag. 23(3) 033007 doi: 10.1117/1.JEI.23.3.033007
Published in: Journal of Electronic Imaging Volume 23, Issue 3
Show Author Affiliations
Minna Qiu, Harbin Institute of Technology (China)
Zhengming Li, Harbin Institute of Technology (China)
Guangdong Polytechnic Normal Univ. (China)
Hongzhi Zhang, Harbin Institute of Technology (China)
Charlene Xie, Harbin Institute of Technology (China)
Jian Zhang, Harbin Institute of Technology (China)

© SPIE. Terms of Use
Back to Top