File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Separable two-dimensional linear discriminant analysis

TitleSeparable two-dimensional linear discriminant analysis
Authors
KeywordsLDA
2DLDA
Two-dimensional data
Face recognition
Issue Date2010
PublisherSpringer-Verlag.
Citation
The 19th International Conference on Computational Statistics (COMPSTAT' 2010), Paris, France, 22-27 August 2010. In Proceedings of COMPSTAT, 2010, pt. 16, p. 597-604 How to Cite?
AbstractSeveral two-dimensional linear discriminant analysis LDA (2DLDA) methods have received much attention in recent years. Among them, the 2DLDA, introduced by Ye, Janardan and Li (2005), is an important development. However, it is found that their proposed iterative algorithm does not guarantee convergence. In this paper, we assume a separable covariance matrix of 2D data and propose separable 2DLDA which can provide a neatly analytical solution similar to that for classical LDA. Empirical results on face recognition demonstrate the superiority of our proposed separable 2DLDA over 2DLDA in terms of classification accuracy and computational efficiency.
Persistent Identifierhttp://hdl.handle.net/10722/127200
ISBN

 

DC FieldValueLanguage
dc.contributor.authorZhao, Jen_HK
dc.contributor.authorYu, PLHen_HK
dc.contributor.authorLi, Sen_HK
dc.date.accessioned2010-10-31T13:11:54Z-
dc.date.available2010-10-31T13:11:54Z-
dc.date.issued2010en_HK
dc.identifier.citationThe 19th International Conference on Computational Statistics (COMPSTAT' 2010), Paris, France, 22-27 August 2010. In Proceedings of COMPSTAT, 2010, pt. 16, p. 597-604en_HK
dc.identifier.isbn9783790826036en_HK
dc.identifier.urihttp://hdl.handle.net/10722/127200-
dc.description.abstractSeveral two-dimensional linear discriminant analysis LDA (2DLDA) methods have received much attention in recent years. Among them, the 2DLDA, introduced by Ye, Janardan and Li (2005), is an important development. However, it is found that their proposed iterative algorithm does not guarantee convergence. In this paper, we assume a separable covariance matrix of 2D data and propose separable 2DLDA which can provide a neatly analytical solution similar to that for classical LDA. Empirical results on face recognition demonstrate the superiority of our proposed separable 2DLDA over 2DLDA in terms of classification accuracy and computational efficiency.-
dc.languageengen_HK
dc.publisherSpringer-Verlag.en_HK
dc.relation.ispartofProceedings of COMPSTAT' 2010en_HK
dc.subjectLDA-
dc.subject2DLDA-
dc.subjectTwo-dimensional data-
dc.subjectFace recognition-
dc.titleSeparable two-dimensional linear discriminant analysisen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailZhao, J: jhzhao1@hku.hken_HK
dc.identifier.emailYu, PLH: plhyu@hku.hken_HK
dc.identifier.emailLi, S: lishulan0526@gmail.com-
dc.identifier.authorityYu, PLH=rp00835en_HK
dc.identifier.doi10.1007/978-3-7908-2604-3_62-
dc.identifier.hkuros178996en_HK
dc.identifier.spage597en_HK
dc.identifier.epage604en_HK
dc.publisher.placeGermany-
dc.description.otherThe 19th International Conference on Computational Statistics (COMPSTAT' 2010), Paris, France, 22-27 August 2010. In Proceedings of COMPSTAT, 2010, pt. 16, p. 597-604-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats