Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | LEE, CH | en_US |
dc.contributor.author | JOSHI, A | en_US |
dc.date.accessioned | 2014-12-08T15:03:06Z | - |
dc.date.available | 2014-12-08T15:03:06Z | - |
dc.date.issued | 1995-11-01 | en_US |
dc.identifier.issn | 0031-3203 | en_US |
dc.identifier.uri | http://dx.doi.org/10.1016/0031-3203(95)00035-X | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/1687 | - |
dc.description.abstract | In 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.iso | en_US | en_US |
dc.subject | CORRESPONDENCE | en_US |
dc.subject | IMAGE SEQUENCE | en_US |
dc.subject | LINE TOKENS | en_US |
dc.subject | MISSING TOKENS | en_US |
dc.subject | PARALLELISM | en_US |
dc.title | ON CORRESPONDENCE, LINE TOKENS AND MISSING TOKENS | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1016/0031-3203(95)00035-X | en_US |
dc.identifier.journal | PATTERN RECOGNITION | en_US |
dc.citation.volume | 28 | en_US |
dc.citation.issue | 11 | en_US |
dc.citation.spage | 1751 | en_US |
dc.citation.epage | 1764 | en_US |
dc.contributor.department | 資訊工程學系 | zh_TW |
dc.contributor.department | Department of Computer Science | en_US |
dc.identifier.wosnumber | WOS:A1995TH02200011 | - |
dc.citation.woscount | 1 | - |
Appears in Collections: | Articles |
Files in This Item:
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.