File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A multi-level supporting scheme for face recognition under partial occlusions and disguise

TitleA multi-level supporting scheme for face recognition under partial occlusions and disguise
Authors
KeywordsDistance-based
Existing method
Face database
Face recognition systems
Issue Date2010
PublisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/
Citation
The 10th Asian Conference on Computer Vision, Queenstown, New Zealand, 8-12 November 2010. In Lecture Notes in Computer Science, 2010, v. 6495, p. 690-701 How to Cite?
AbstractFace recognition has always been a challenging task in real-life surveillance videos, with partial occlusion being one of the key factors affecting the robustness of face recognition systems. Previous researches had approached the problem of face recognition with partial occlusions by dividing a face image into local patches, and training an independent classifier for each local patch. The final recognition result was then decided by integrating the results of all local patch classifiers. Such a local approach, however, ignored all the crucial distinguishing information presented in the global holistic faces. Instead of using only local patch classifiers, this paper presents a novel multi-level supporting scheme which incorporates patch classifiers at multiple levels, including both the global holistic face and local face patches at different levels. This supporting scheme employs a novel criteria-based class candidates selection process. This selection process preserves more class candidates for consideration as the final recognition results when there are conflicts between patch classifiers, while enables a fast decision making when most of the classifiers conclude to the same set of class candidates. All the patch classifiers will contribute their supports to each selected class candidate. The support of each classifier is defined as a simple distance-based likelihood ratio, which effectively enhances the effect of a 'more-confident' classifier. The proposed supporting scheme is evaluated using the AR face database which contains faces with different facial expressions and face occlusions in real scenarios. Experimental results show that the proposed supporting scheme gives a high recognition rate, and outperforms other existing methods. © 2011 Springer-Verlag Berlin Heidelberg.
DescriptionLNCS v. 6495 is proceedings of the 10th Asian Conference on Computer Vision, AACV 2010 (pt. 4)
Persistent Identifierhttp://hdl.handle.net/10722/129005
ISSN
2023 SCImago Journal Rankings: 0.606
References

 

DC FieldValueLanguage
dc.contributor.authorYuk, JSC-
dc.contributor.authorWong, KKY-
dc.contributor.authorChung, RHY-
dc.date.accessioned2010-12-09T07:15:22Z-
dc.date.available2010-12-09T07:15:22Z-
dc.date.issued2010-
dc.identifier.citationThe 10th Asian Conference on Computer Vision, Queenstown, New Zealand, 8-12 November 2010. In Lecture Notes in Computer Science, 2010, v. 6495, p. 690-701-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/129005-
dc.descriptionLNCS v. 6495 is proceedings of the 10th Asian Conference on Computer Vision, AACV 2010 (pt. 4)-
dc.description.abstractFace recognition has always been a challenging task in real-life surveillance videos, with partial occlusion being one of the key factors affecting the robustness of face recognition systems. Previous researches had approached the problem of face recognition with partial occlusions by dividing a face image into local patches, and training an independent classifier for each local patch. The final recognition result was then decided by integrating the results of all local patch classifiers. Such a local approach, however, ignored all the crucial distinguishing information presented in the global holistic faces. Instead of using only local patch classifiers, this paper presents a novel multi-level supporting scheme which incorporates patch classifiers at multiple levels, including both the global holistic face and local face patches at different levels. This supporting scheme employs a novel criteria-based class candidates selection process. This selection process preserves more class candidates for consideration as the final recognition results when there are conflicts between patch classifiers, while enables a fast decision making when most of the classifiers conclude to the same set of class candidates. All the patch classifiers will contribute their supports to each selected class candidate. The support of each classifier is defined as a simple distance-based likelihood ratio, which effectively enhances the effect of a 'more-confident' classifier. The proposed supporting scheme is evaluated using the AR face database which contains faces with different facial expressions and face occlusions in real scenarios. Experimental results show that the proposed supporting scheme gives a high recognition rate, and outperforms other existing methods. © 2011 Springer-Verlag Berlin Heidelberg.-
dc.languageeng-
dc.publisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/-
dc.relation.ispartofLecture Notes in Computer Science-
dc.rightsThe original publication is available at www.springerlink.com-
dc.subjectDistance-based-
dc.subjectExisting method-
dc.subjectFace database-
dc.subjectFace recognition systems-
dc.titleA multi-level supporting scheme for face recognition under partial occlusions and disguiseen_US
dc.typeConference_Paperen_US
dc.identifier.emailYuk, JSC: scyuk@hku.hk-
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.identifier.emailChung, RHY: hychung@cs.hku.hk-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-642-19282-1_55-
dc.identifier.scopuseid_2-s2.0-79952496250-
dc.identifier.hkuros183233-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-79952496250&selection=ref&src=s&origin=recordpage-
dc.identifier.volume6495-
dc.identifier.spage690-
dc.identifier.epage701-
dc.publisher.placeGermany-
dc.description.otherThe 10th Asian Conference on Computer Vision, Queenstown, New Zealand, 8-12 November 2010. In Lecture Notes in Computer Science, 2010, v. 6495, p. 690-701-
dc.identifier.scopusauthoridYuk, JSC=18042591200-
dc.identifier.scopusauthoridWong, KYK=24402187900-
dc.identifier.scopusauthoridChung, RHY=14059962600-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats