Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/29514
DC FieldValueLanguage
dc.contributorDepartment of Computing-
dc.creatorJing, XY-
dc.creatorLan, C-
dc.creatorZhang, D-
dc.creatorYang, JY-
dc.creatorLi, M-
dc.creatorLi, S-
dc.creatorZhu, SH-
dc.date.accessioned2014-12-31T08:01:10Z-
dc.date.available2014-12-31T08:01:10Z-
dc.identifier.issn0167-8655-
dc.identifier.urihttp://hdl.handle.net/10397/29514-
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.subjectDiscriminant SMPP (DSMPP)en_US
dc.subjectDual-objective optimizationen_US
dc.subjectFace recognitionen_US
dc.subjectManifold learningen_US
dc.subjectSubclass discriminant analysisen_US
dc.subjectSubclass-center manifold preserving projection (SMPP)en_US
dc.titleFace feature extraction and recognition based on discriminant subclass-center manifold preserving projectionen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage709-
dc.identifier.epage717-
dc.identifier.volume33-
dc.identifier.issue6-
dc.identifier.doi10.1016/j.patrec.2012.01.001-
dcterms.abstractManifold learning is an effective dimensional reduction technique for face feature extraction, which, generally speaking, tends to preserve the local neighborhood structures of given samples. However, neighbors of a sample often comprise more inter-class data than intra-class data, which is an undesirable effect for classification. In this paper, we address this problem by proposing a subclass-center based manifold preserving projection (SMPP) approach, which aims at preserving the local neighborhood structure of subclass-centers instead of given samples. We theoretically show from a probability perspective that, neighbors of a subclass-center would comprise of more intra-class data than inter-class data, and thus is more desirable for classification. In order to take full advantage of the class separability, we further propose the discriminant SMPP (DSMPP) approach, which incorporates the subclass discriminant analysis (SDA) technique to SMPP. In contrast to related discriminant manifold learning methods, DSMPP is formulated as a dual-objective optimization problem and we present analytical solution to it. Experimental results on the public AR, FERET and CAS-PEAL face databases demonstrate that the proposed approaches are more effective than related manifold learning and discriminant manifold learning methods in classification performance.-
dcterms.bibliographicCitationPattern recognition letters, 2012, v. 33, no. 6, p. 709-717-
dcterms.isPartOfPattern recognition letters-
dcterms.issued2012-
dc.identifier.isiWOS:000301999500005-
dc.identifier.scopus2-s2.0-84862793473-
dc.identifier.eissn1872-7344-
Appears in Collections:Journal/Magazine Article
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

SCOPUSTM   
Citations

5
Last Week
0
Last month
0
Citations as of Aug 29, 2020

WEB OF SCIENCETM
Citations

4
Last Week
0
Last month
0
Citations as of Sep 26, 2020

Page view(s)

178
Last Week
0
Last month
Citations as of Sep 28, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.