THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
A cubist Apprach to Object Recognition
UR > CS > Research > Vision > Publications > 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. }
}