Face Recognition from One Example View

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6640

Full metadata record

DC Field	Value	Language
dc.creator	Beymer, David	-
dc.creator	Poggio, Tomaso	-
dc.date	2004-10-08T20:36:05Z	-
dc.date	2004-10-08T20:36:05Z	-
dc.date	1995-09-01	-
dc.date.accessioned	2013-10-09T02:46:20Z	-
dc.date.available	2013-10-09T02:46:20Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1536	-
dc.identifier	http://hdl.handle.net/1721.1/6640	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	If we are provided a face database with only one example view per person, is it possible to recognize new views of them under a variety of different poses, especially views rotated in depth from the original example view? We investigate using prior knowledge about faces plus each single example view to generate virtual views of each person, or views of the face as seen from different poses. Prior knowledge of faces is represented in an example-based way, using 2D views of a prototype face seen rotating in depth. The synthesized virtual views are evaluated as example views in a view-based approach to pose-invariant face recognition. They are shown to improve the recognition rate over the scenario where only the single real view is used.	-
dc.format	6363024 bytes	-
dc.format	1327503 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1536	-
dc.title	Face Recognition from One Example View	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI