Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/5968

Full metadata record

DC Field	Value	Language
dc.creator	Poggio, Tomaso	-
dc.creator	Vetter, Thomas	-
dc.date	2004-10-04T14:24:21Z	-
dc.date	2004-10-04T14:24:21Z	-
dc.date	1992-02-01	-
dc.date.accessioned	2013-10-09T02:42:09Z	-
dc.date.available	2013-10-09T02:42:09Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1347	-
dc.identifier	http://hdl.handle.net/1721.1/5968	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	In this note we discuss how recognition can be achieved from a single 2D model view exploiting prior knowledge of an object's structure (e.g. symmetry). We prove that for any bilaterally symmetric 3D object one non- accidental 2D model view is sufficient for recognition. Symmetries of higher order allow the recovery of structure from one 2D view. Linear transformations can be learned exactly from a small set of examples in the case of "linear object classes" and used to produce new views of an object from a single view.	-
dc.format	22 p.	-
dc.format	1962838 bytes	-
dc.format	1538757 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1347	-
dc.subject	object recognition	-
dc.subject	class and prototypes	-
dc.subject	symmetry	-
dc.subject	learning	-
dc.title	Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI