Probabilistic Solution of Ill-Posed Problems in Computational Vision

dc.creator	Marroquin, J.
dc.creator	Mitter, S.
dc.creator	Poggio, T.
dc.date	2004-10-04T14:56:53Z
dc.date	2004-10-04T14:56:53Z
dc.date	1987-03-01
dc.date.accessioned	2013-10-09T02:45:28Z
dc.date.available	2013-10-09T02:45:28Z
dc.date.issued	2013-10-09
dc.identifier	AIM-897
dc.identifier	http://hdl.handle.net/1721.1/6449
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	We formulate several problems in early vision as inverse problems. Among the solution methods we review standard regularization theory, discuss its limitations, and present new stochastic (in particular, Bayesian) techniques based on Markov Random Field models for their solution. We derive efficient algorithms and describe parallel implementations on digital parallel SIMD architectures, as well as a new class of parallel hybrid computers that mix digital with analog components.
dc.format	5330897 bytes
dc.format	2064608 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-897
dc.title	Probabilistic Solution of Ill-Posed Problems in Computational Vision

Files in this item

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