THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
3D Recogniton via 2-Stage Associative Memory |
pdf 278 KB
ps.gz 993 KB
ps 2.74 MB
@TechReport{Nelson:TR95b,
author = {Randal C. Nelson},
title = {3D Recogniton via 2-Stage Associative Memory},
institution = {Comp Sci Dept University of Rochester},
year = {1995},
number = {565},
address = {Rochester NY},
month = {January},
abstract = {
We describe a method of 3-D object recognition based on two stage use of a
general purpose associative memory and a principal views representation. The
basic idea is to make use of semi-invariant objects called keys. A key is any
robustly extractable feature that has sufficient information content to specify
a 2-D configuration of an associated object (location, scale, orientation)
plus sufficient additional parameters to provide efficient indexing and
meaningful verification. The recognition system utilizes an associative memory
organized so that access via a key feature evokes associated hypotheses for
the identity and configuration of all objects that could have produced it.
These hypothesis are fed into a second stage associative memory, which
maintains a probabilistic estimate of the likelihood of each hypothesis based
on statistics about the occurrence of the keys in the primary database. Because
it is based on a merged percept of local features rather than global
properties, the method is robust to occlusion and background clutter, and does
not require prior segmentation. Entry of objects into the memory is an active,
automatic procedure. We have implemented a version of the system that allows
arbitrary definitions for key features. Experiments using keys based on
perceptual groups of line segments are reported. Good results were obtained on
a database derived from of approximately 150 images representing different
views of 7 polyhedral objects. }
}