THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
A cubist Apprach to Object Recognition |
pdf 423 KB
ps.gz 2.65 MB
ps 9.46 MB
@InProceedings{Nelson:98,
author = {Randal C. Nelson and Andrea Selinger},
title = {A cubist Apprach to Object Recognition},
booktitle = {International Conference on Computer Vision (ICCV(98)},
pages = {614-621},
year = {1998},
address = {Bombay, India},
month = {January},
abstract = { We describe an appearancebased object recogni
tion system using a keyed, multilevel context rep
resentation 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 sys
tem demonstrates good recognition of a variety of 3
D shapes, ranging from sports cars and fighter planes
to snakes and lizards with full orthographic invari
ance. We report the results of largescale tests, in
volving over 2000 separate test images, that evalu
ate 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 modeled. To
our knowledge, the results we report are the best in the
literature for fullsphere tests of general shapes with
occlusion and clutter resistance. }
}