File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Conference Paper: Novel gait recognition technique based on SVM fusion of PCA-processed contour projection and skeleton model features

TitleNovel gait recognition technique based on SVM fusion of PCA-processed contour projection and skeleton model features
Authors
KeywordsContour Projection
Gait Recognition
Principal Component Analysis
Support Vector Machine
Issue Date2009
PublisherIEEE.
Citation
The 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA 2009), Hong Kong, China, 11-13 May 2009. In Conference Proceedings, 2009, p. 1-4 How to Cite?
AbstractGait is a potential behavioral feature, and many allied studies have demonstrated that it can be served as a useful biometric feature for recognition. This paper described a novel gait recognition technique based on support vector machine fusion of contour projection and skeleton model features. A principal component analysis method was used to lower the dimension of contour projection after segmenting silhouettes from the background in the key frame of gait picture sequence and a skeleton model was built to produce other shape features. The combining features were fused by a support vector machine and tested on the CASIA database at the feature level and decision level based on posterior probability. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.
Persistent Identifierhttp://hdl.handle.net/10722/62542
ISBN
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorMing, Den_HK
dc.contributor.authorBai, YRen_HK
dc.contributor.authorZhang, Cen_HK
dc.contributor.authorWan, BKen_HK
dc.contributor.authorHu, Yen_HK
dc.contributor.authorLuk, KDKen_HK
dc.date.accessioned2010-07-13T04:03:35Z-
dc.date.available2010-07-13T04:03:35Z-
dc.date.issued2009en_HK
dc.identifier.citationThe 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA 2009), Hong Kong, China, 11-13 May 2009. In Conference Proceedings, 2009, p. 1-4en_HK
dc.identifier.isbn978-1-4244-3819-8-
dc.identifier.issn2159-1547-
dc.identifier.urihttp://hdl.handle.net/10722/62542-
dc.description.abstractGait is a potential behavioral feature, and many allied studies have demonstrated that it can be served as a useful biometric feature for recognition. This paper described a novel gait recognition technique based on support vector machine fusion of contour projection and skeleton model features. A principal component analysis method was used to lower the dimension of contour projection after segmenting silhouettes from the background in the key frame of gait picture sequence and a skeleton model was built to produce other shape features. The combining features were fused by a support vector machine and tested on the CASIA database at the feature level and decision level based on posterior probability. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.-
dc.languageengen_HK
dc.publisherIEEE.-
dc.relation.ispartofProceedings of IEEE International Conference on Computational Intelligence for Measurement Systems & Applications, CIMSA 2009-
dc.subjectContour Projection-
dc.subjectGait Recognition-
dc.subjectPrincipal Component Analysis-
dc.subjectSupport Vector Machine-
dc.titleNovel gait recognition technique based on SVM fusion of PCA-processed contour projection and skeleton model featuresen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailHu, Y:yhud@hku.hken_HK
dc.identifier.emailLuk, KDK:hcm21000@hku.hken_HK
dc.identifier.authorityHu, Y=rp00432en_HK
dc.identifier.authorityLuk, KDK=rp00333en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CIMSA.2009.5069906-
dc.identifier.scopuseid_2-s2.0-77950801418-
dc.identifier.hkuros159911en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-77950801418&selection=ref&src=s&origin=recordpage-
dc.identifier.spage1-
dc.identifier.epage4-
dc.identifier.scopusauthoridMing, D=9745824400-
dc.identifier.scopusauthoridBai, Y=35108689200-
dc.identifier.scopusauthoridZhang, C=35110047100-
dc.identifier.scopusauthoridWan, B=7102316798-
dc.identifier.scopusauthoridHu, Y=7407116091-
dc.identifier.scopusauthoridLuk, KDK=7201921573-
dc.customcontrol.immutablesml 170630 merged-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats