Object Recognition By Alignment Using Invariant Projections of Planar Surfaces

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6623

Full metadata record

DC Field	Value	Language
dc.creator	Nagao, Kanji	-
dc.creator	Grimson W. Eric L.	-
dc.date	2004-10-08T20:34:39Z	-
dc.date	2004-10-08T20:34:39Z	-
dc.date	1994-02-01	-
dc.date.accessioned	2013-10-09T02:46:10Z	-
dc.date.available	2013-10-09T02:46:10Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1463	-
dc.identifier	http://hdl.handle.net/1721.1/6623	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotations in the image field. To use this property, we propose a new alignment approach to object recognition based on centroid alignment of corresponding feature groups. This method uses only a single pair of 2D model and data. Experimental results show the robustness of the proposed method against perturbations of feature positions.	-
dc.format	214263 bytes	-
dc.format	569720 bytes	-
dc.format	application/octet-stream	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1463	-
dc.title	Object Recognition By Alignment Using Invariant Projections of Planar Surfaces	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI