What Makes a Good Feature?

dc.creator	Richards, W.
dc.creator	Jepson, A.
dc.date	2004-10-04T14:24:15Z
dc.date	2004-10-04T14:24:15Z
dc.date	1992-04-01
dc.date.accessioned	2013-10-09T02:42:07Z
dc.date.available	2013-10-09T02:42:07Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1356
dc.identifier	http://hdl.handle.net/1721.1/5963
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Using a Bayesian framework, we place bounds on just what features are worth computing if inferences about the world properties are to be made from image data. Previously others have proposed that useful features reflect "non-accidental'' or "suspicious'' configurations (such as parallel or colinear lines). We make these notions more precise and show them to be context sensitive.
dc.format	42 p.
dc.format	2433280 bytes
dc.format	1910701 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1356
dc.subject	computational vision
dc.subject	vision features
dc.subject	Bayesian model
dc.subject	svision psychophysics
dc.subject	color
dc.subject	motion
dc.title	What Makes a Good Feature?

Files in this item

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