Next Article in Journal
Analysis of Scholarly Communication Activities in Buddhism and Buddhist Studies
Previous Article in Journal / Special Issue
Analysis and Visualization for Hot Spot Based Route Recommendation Using Short-Dated Taxi GPS Traces
Article Menu

Export Article

Open AccessArticle
Information 2015, 6(2), 152-161; doi:10.3390/info6020152

Graph Regularized Within-Class Sparsity Preserving Projection for Face Recognition

Institute of Image Processing & Pattern Recognition, Tai Zhou University, Taizhou 318000, China
*
Author to whom correspondence should be addressed.
Academic Editor: Willy Susilo
Received: 18 December 2014 / Revised: 2 April 2015 / Accepted: 10 April 2015 / Published: 24 April 2015
(This article belongs to the Special Issue Intelligent Data Analysis)
View Full-Text   |   Download PDF [318 KB, uploaded 27 April 2015]   |  

Abstract

As a dominant method for face recognition, the subspace learning algorithm shows desirable performance. Manifold learning can deal with the nonlinearity hidden in the data, and can project high dimensional data onto low dimensional data while preserving manifold structure. Sparse representation shows its robustness for noises and is very practical for face recognition. In order to extract the facial features from face images effectively and robustly, in this paper, a method called graph regularized within-class sparsity preserving analysis (GRWSPA) is proposed, which can preserve the within-class sparse reconstructive relationship and enhances separatability for different classes. Specifically, for each sample, we use the samples in the same class (except itself) to represent it, and keep the reconstructive weight unchanged during projection. To preserve the manifold geometry structure of the original space, one adjacency graph is constructed to characterize the interclass separability and is incorporated into its criteria equation as a constraint in a supervised manner. As a result, the features extracted are sparse and discriminative and helpful for classification. Experiments are conducted on the two open face databases, the ORL and YALE face databases, and the results show that the proposed method can effectively and correctly find the key facial features from face images and can achieve better recognition rate compared with other existing ones. View Full-Text
Keywords: dimensionality reduction; sparse representation; graph embedding; face recognition dimensionality reduction; sparse representation; graph embedding; face recognition
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Lou, S.; Zhao, X.; Guo, W.; Chen, Y. Graph Regularized Within-Class Sparsity Preserving Projection for Face Recognition. Information 2015, 6, 152-161.

Show more citation formats Show less citations formats

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Information EISSN 2078-2489 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top