The Role of Knowledge in Visual Shape Representation

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6833

Full metadata record

DC Field	Value	Language
dc.creator	Saund, Eric	-
dc.date	2004-10-20T20:00:44Z	-
dc.date	2004-10-20T20:00:44Z	-
dc.date	1988-10-01	-
dc.date.accessioned	2013-10-09T02:47:10Z	-
dc.date.available	2013-10-09T02:47:10Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AITR-1092	-
dc.identifier	http://hdl.handle.net/1721.1/6833	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes.	-
dc.format	300 p.	-
dc.format	38394678 bytes	-
dc.format	31060480 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AITR-1092	-
dc.subject	shape representation	-
dc.subject	dimensionality-reduction	-
dc.subject	knowledge	-
dc.subject	sscale-space	-
dc.subject	later vision	-
dc.title	The Role of Knowledge in Visual Shape Representation	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI