A Computational Model for Visual Selection

A Computational Model for Visual Selection (1999)

Cached

Download Links

[galton.uchicago.edu]
[www.math.umass.edu]

Other Repositories/Bibliography

DBLP

by Yali Amit , Donald Geman

Venue:	NEURAL COMPUTATION
Citations:	77 - 14 self

Versions

Version History

Metadata Version 4

User correction supplied by mph

Datum	Value	Source
TITLE	A Computational Model for Visual Selection	user correction - Legacy Corrections
AUTHOR NAME	Yali Amit	user correction
AUTHOR AFFIL	Department of Statistics, University of Chicago	user correction
AUTHOR ADDR	Chicago, IL 60637	user correction
AUTHOR NAME	Donald Geman	user correction
AUTHOR AFFIL	Department of Statistics, University of Chicago, Chicago	user correction
AUTHOR ADDR	IL, 60637	user correction
ABSTRACT	We propose a computational model for detecting and localizing instances from an object class in static grey level images. We divide detection into visual selection and final classification, concentrating on the former: Drastically reducing the number of candidate regions which require further, usually more intensive, processing, but with a minimum of computation and missed detections. Bottom-up processing is based on local groupings of edge fragments constrained by loose geometrical relationships. They have no a priori semantic or geometric interpretation. The role of training is to select special groupings which are moderately likely at certain places on the object but rare in the background. We show that the statistics in both populations are stable. The candidate regions are those which contain global arrangements of several local groupings. Whereas our model was not conceived to explain brain functions, it does cohere with evidence about the functions of neurons in V1 and V2, such ...	user correction - Legacy Corrections
YEAR	1999	INFERENCE
VENUE	NEURAL COMPUTATION	user correction
VENUE TYPE	JOURNAL	INFERENCE
PAGES	1691--1715	INFERENCE
VOLUME	11	INFERENCE
CITATIONS	26 found	ParsCit 1.0