THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
A Cubist Approach to Object Recognition |
pdf 1.24 MB
ps.gz 9.38 MB
ps 32.98 MB
@TechReport{Nelson:TR98,
author = {Randal C. Nelson and Andrea Selinger},
title = {A Cubist Approach to Object Recognition},
institution = {Comp. Sci. Dept. University of Rochester},
year = {1998},
number = {689},
address = {Rochester NY},
month = {May},
abstract = {#
We describe an appearance-based object recognition system using a keyed,
multi-level context representation reminiscent of certain aspects of cubist
art. Specifically, we utilize distinctive intermediate-level features, in
this case automatically extracted 2D boundary fragments, as keys, which are
then verified within a local context, and assembled within a loose global
context to evoke an overall percept. This system demonstrates extraordinarly
good recognition of a variety of 3D shapes, ranging from sports cars and
fighter planes to snakes and lizards with full orthographic invariance. We
report the results of large-scale tests, involving over 2000 separate test
images, that evaluate performance with increasing number of items in the
database, in the presence of clutter, background change, and occlusion, and
also the results of some generic classification experiments where the system
is tested on objects never previously seen or modelled. To our knowledge,
the results we report are the best in the literature for full-sphere tests
of general shapes with occlusion and clutter resistance. }
}