Parallel and Deterministic Algorithms for MRFs: Surface Reconstruction and Integration

dc.creator	Geiger, Davi
dc.creator	Girosi, Federico
dc.date	2004-10-04T14:36:13Z
dc.date	2004-10-04T14:36:13Z
dc.date	1989-05-01
dc.date.accessioned	2013-10-09T02:42:26Z
dc.date.available	2013-10-09T02:42:26Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1114
dc.identifier	http://hdl.handle.net/1721.1/6025
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	In recent years many researchers have investigated the use of Markov random fields (MRFs) for computer vision. The computational complexity of the implementation has been a drawback of MRFs. In this paper we derive deterministic approximations to MRFs models. All the theoretical results are obtained in the framework of the mean field theory from statistical mechanics. Because we use MRFs models the mean field equations lead to parallel and iterative algorithms. One of the considered models for image reconstruction is shown to give in a natural way the graduate non-convexity algorithm proposed by Blake and Zisserman.
dc.format	37 p.
dc.format	3090418 bytes
dc.format	2411062 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1114
dc.subject	surface reconstruction
dc.subject	Markov random fields
dc.subject	mean field
dc.subject	sintegration
dc.subject	parameter estimation
dc.subject	deterministic algorithms
dc.title	Parallel and Deterministic Algorithms for MRFs: Surface Reconstruction and Integration

Files in this item

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