DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, H | ko |
dc.contributor.author | Kim, Seong-Dae | ko |
dc.contributor.author | Choi, HC | ko |
dc.date.accessioned | 2013-03-07T11:31:52Z | - |
dc.date.available | 2013-03-07T11:31:52Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2007-07 | - |
dc.identifier.citation | PATTERN RECOGNITION LETTERS, v.28, pp.1077 - 1082 | - |
dc.identifier.issn | 0167-8655 | - |
dc.identifier.uri | http://hdl.handle.net/10203/90081 | - |
dc.description.abstract | Elastic graph matching (EGM) is a well-known approach in face recognition area for the robust face recognition to a rotation in depth and facial expression change. We extended the conventional EGM to the generalized EGM (G-EGM), which is afford to handle even globally warped faces, by enhancing the robustness of node descriptors to a global warping, and introducing warping-compensated edges in graph matching cost function. The improved performance of the G-EGM was evaluated through the recognition simulation based on arbitrary posed faces. (c) 2007 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE BV | - |
dc.subject | AUTHENTICATION | - |
dc.title | Generalized elastic graph matching for face recognition | - |
dc.type | Article | - |
dc.identifier.wosid | 000246378100009 | - |
dc.identifier.scopusid | 2-s2.0-34147127513 | - |
dc.type.rims | ART | - |
dc.citation.volume | 28 | - |
dc.citation.beginningpage | 1077 | - |
dc.citation.endingpage | 1082 | - |
dc.citation.publicationname | PATTERN RECOGNITION LETTERS | - |
dc.identifier.doi | 10.1016/j.patrec.2007.01.003 | - |
dc.contributor.localauthor | Kim, Seong-Dae | - |
dc.contributor.nonIdAuthor | Shin, H | - |
dc.contributor.nonIdAuthor | Choi, HC | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | face recognition | - |
dc.subject.keywordAuthor | face alignment | - |
dc.subject.keywordAuthor | elastic graph matching | - |
dc.subject.keywordPlus | AUTHENTICATION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.