Show simple item record

Machine Recognition as Representation and Search

dc.date.accessioned2004-10-04T14:35:37Z
dc.date.accessioned2018-11-24T10:11:29Z
dc.date.available2004-10-04T14:35:37Z
dc.date.available2018-11-24T10:11:29Z
dc.date.issued1989-12-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6003
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/6003
dc.description.abstractGenerality, representation, and control have been the central issues in machine recognition. Model-based recognition is the search for consistent matches of the model and image features. We present a comparative framework for the evaluation of different approaches, particularly those of ACRONYM, RAF, and Ikeuchi et al. The strengths and weaknesses of these approaches are discussed and compared and the remedies are suggested. Various tradeoffs made in the implementations are analyzed with respect to the systems' intended task-domains. The requirements for a versatile recognition system are motivated. Several directions for future research are pointed out.en_US
dc.format.extent40 p.en_US
dc.format.extent6338900 bytes
dc.format.extent2496576 bytes
dc.language.isoen_US
dc.subjectcomputer visionen_US
dc.subjectrepresentationen_US
dc.subjectsearch controlen_US
dc.subjectobjectsmodelingen_US
dc.subjectconsistent labelingen_US
dc.subjectmodel-based recognitionen_US
dc.titleMachine Recognition as Representation and Searchen_US


Files in this item

FilesSizeFormatView
AIM-1189.pdf2.496Mbapplication/pdfView/Open
AIM-1189.ps6.338Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record