Regularized locality preserving discriminant embedding for face recognition

For face recognition, graph embedding techniques attempt to produce a high data locality projection for better recognition performance. However, estimation of population data locality could be severely biased due to small number of training samples. The biased estimation triggers overfitting problem...

Full description

Bibliographic Details
Main Authors: Pang, Ying Han, Teoh, Andrew Beng Jin, Abas, Fazly Salleh
Format: Article
Language:English
Published: Elsevier Science 2012
Subjects:
Online Access:http://shdl.mmu.edu.my/3387/
http://shdl.mmu.edu.my/3387/1/Regularized%20Locality%20Preserving%20Discriminant%20Embedding%20for%20Face%20Recognition.pdf
_version_ 1848790314000580608
author Pang, Ying Han
Teoh, Andrew Beng Jin
Abas, Fazly Salleh
author_facet Pang, Ying Han
Teoh, Andrew Beng Jin
Abas, Fazly Salleh
author_sort Pang, Ying Han
building MMU Institutional Repository
collection Online Access
description For face recognition, graph embedding techniques attempt to produce a high data locality projection for better recognition performance. However, estimation of population data locality could be severely biased due to small number of training samples. The biased estimation triggers overfitting problem and hence poor generalization. In this paper, we propose a new linear graph embedding technique based upon an adaptive locality preserving regulation model (ALPRM), known as Regularized Locality Preserving Discriminant Embedding (RLPDE). In RLPDE, the projection features are regulated based on ALPRM to approach population data locality, which can directly enhance the locality preserving capability of the projection features. This paper also presents the relation between locality preserving capability and class discrimination. Specifically, we show that the optimization of the locality preserving function minimizes the within-class variability. Experiments on three face datasets such as PIE, FRGC and FERET show the promising performance of the proposed technique. (C) 2011 Elsevier B.V. All rights reserved.
first_indexed 2025-11-14T18:10:38Z
format Article
id mmu-3387
institution Multimedia University
institution_category Local University
language English
last_indexed 2025-11-14T18:10:38Z
publishDate 2012
publisher Elsevier Science
recordtype eprints
repository_type Digital Repository
spelling mmu-33872017-01-05T04:15:57Z http://shdl.mmu.edu.my/3387/ Regularized locality preserving discriminant embedding for face recognition Pang, Ying Han Teoh, Andrew Beng Jin Abas, Fazly Salleh QA75.5-76.95 Electronic computers. Computer science For face recognition, graph embedding techniques attempt to produce a high data locality projection for better recognition performance. However, estimation of population data locality could be severely biased due to small number of training samples. The biased estimation triggers overfitting problem and hence poor generalization. In this paper, we propose a new linear graph embedding technique based upon an adaptive locality preserving regulation model (ALPRM), known as Regularized Locality Preserving Discriminant Embedding (RLPDE). In RLPDE, the projection features are regulated based on ALPRM to approach population data locality, which can directly enhance the locality preserving capability of the projection features. This paper also presents the relation between locality preserving capability and class discrimination. Specifically, we show that the optimization of the locality preserving function minimizes the within-class variability. Experiments on three face datasets such as PIE, FRGC and FERET show the promising performance of the proposed technique. (C) 2011 Elsevier B.V. All rights reserved. Elsevier Science 2012-02 Article PeerReviewed text en http://shdl.mmu.edu.my/3387/1/Regularized%20Locality%20Preserving%20Discriminant%20Embedding%20for%20Face%20Recognition.pdf Pang, Ying Han and Teoh, Andrew Beng Jin and Abas, Fazly Salleh (2012) Regularized locality preserving discriminant embedding for face recognition. Neurocomputing, 77 (1). pp. 156-166. ISSN 0925-2312 http://dx.doi.org/10.1016/j.neucom.2011.09.007 doi:10.1016/j.neucom.2011.09.007 doi:10.1016/j.neucom.2011.09.007
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Pang, Ying Han
Teoh, Andrew Beng Jin
Abas, Fazly Salleh
Regularized locality preserving discriminant embedding for face recognition
title Regularized locality preserving discriminant embedding for face recognition
title_full Regularized locality preserving discriminant embedding for face recognition
title_fullStr Regularized locality preserving discriminant embedding for face recognition
title_full_unstemmed Regularized locality preserving discriminant embedding for face recognition
title_short Regularized locality preserving discriminant embedding for face recognition
title_sort regularized locality preserving discriminant embedding for face recognition
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/3387/
http://shdl.mmu.edu.my/3387/
http://shdl.mmu.edu.my/3387/
http://shdl.mmu.edu.my/3387/1/Regularized%20Locality%20Preserving%20Discriminant%20Embedding%20for%20Face%20Recognition.pdf