| | |
Summary: A Computational Model
for Visual Selection
Yali Amit and Donald Geman y
February 1998
Department of Statistics, University of Chicago, Chicago, IL, 60637; Email:
amit@galton.uchicago.edu. Supported in part by the Army Research O ce under grant
DAAH04-96-1-0061 and MURI grant DAAH04-96-1-0445,
yDepartment of Mathematics and Statistics, University of Massachusetts, Amherst, MA 01003;
Email:geman@math.umass.edu. Supported in part by the NSF under grant DMS-9217655, ONR
under contract N00014-97-1-0249, Army Research O ce under MURI grant DAAH04-96-1-0445.
1
Abstract
We propose a computational model for detecting and localizing instances
from an object class in static grey level images. We divide detection into vi-
sual selection and nal classi cation, 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 detec-
tions. 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
|
