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