Show simple item record

dc.contributor.authorCass, Todd A.en_US
dc.date.accessioned2004-10-20T19:58:22Z
dc.date.available2004-10-20T19:58:22Z
dc.date.issued1988-05-01en_US
dc.identifier.otherAITR-1132en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6823
dc.description.abstractTechniques, suitable for parallel implementation, for robust 2D model-based object recognition in the presence of sensor error are studied. Models and scene data are represented as local geometric features and robust hypothesis of feature matchings and transformations is considered. Bounds on the error in the image feature geometry are assumed constraining possible matchings and transformations. Transformation sampling is introduced as a simple, robust, polynomial-time, and highly parallel method of searching the space of transformations to hypothesize feature matchings. Key to the approach is that error in image feature measurement is explicitly accounted for. A Connection Machine implementation and experiments on real images are presented.en_US
dc.format.extent106 p.en_US
dc.format.extent10585533 bytes
dc.format.extent7511134 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesAITR-1132en_US
dc.subjectobject recognitionen_US
dc.subjectobject localizationen_US
dc.subjectparallel computationen_US
dc.subjectsensor uncertaintyen_US
dc.subjecthough transformen_US
dc.titleRobust 2-D Model-Based Object Recognitionen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record