Full metadata record
DC FieldValueLanguage
dc.contributor.authorLEE, CHen_US
dc.contributor.authorJOSHI, Aen_US
dc.date.accessioned2014-12-08T15:03:06Z-
dc.date.available2014-12-08T15:03:06Z-
dc.date.issued1995-11-01en_US
dc.identifier.issn0031-3203en_US
dc.identifier.urihttp://dx.doi.org/10.1016/0031-3203(95)00035-Xen_US
dc.identifier.urihttp://hdl.handle.net/11536/1687-
dc.description.abstractIn this article, the authors expand on some of their previous work on correspondence and propose a system that can correspond in the presence of both point and line tokens, or a mix of them. It can also work if some tokens present in one frame are not present in the other. The proposed algorithm is an amalgamation of reductionist and holist paradigms. We establish that properties which remain invariant for whole image sequences and sequences consisting of corresponding parts from each image frame can be used to establish correspondence. Extensive computer simulation results on synthesised data as well as real image sequences are presented to validate our claims.en_US
dc.language.isoen_USen_US
dc.subjectCORRESPONDENCEen_US
dc.subjectIMAGE SEQUENCEen_US
dc.subjectLINE TOKENSen_US
dc.subjectMISSING TOKENSen_US
dc.subjectPARALLELISMen_US
dc.titleON CORRESPONDENCE, LINE TOKENS AND MISSING TOKENSen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/0031-3203(95)00035-Xen_US
dc.identifier.journalPATTERN RECOGNITIONen_US
dc.citation.volume28en_US
dc.citation.issue11en_US
dc.citation.spage1751en_US
dc.citation.epage1764en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:A1995TH02200011-
dc.citation.woscount1-
Appears in Collections:Articles


Files in This Item:

  1. A1995TH02200011.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.