Robust 2-D Model-Based Object Recognition

dc.creator	Cass, Todd A.
dc.date	2004-10-20T19:58:22Z
dc.date	2004-10-20T19:58:22Z
dc.date	1988-05-01
dc.date.accessioned	2013-10-09T02:47:06Z
dc.date.available	2013-10-09T02:47:06Z
dc.date.issued	2013-10-09
dc.identifier	AITR-1132
dc.identifier	http://hdl.handle.net/1721.1/6823
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Techniques, 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.
dc.format	106 p.
dc.format	10585533 bytes
dc.format	7511134 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AITR-1132
dc.subject	object recognition
dc.subject	object localization
dc.subject	parallel computation
dc.subject	sensor uncertainty
dc.subject	hough transform
dc.title	Robust 2-D Model-Based Object Recognition

Files in this item

Files	Size	Format	View
There are no files associated with this item.