THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Large-Scale Tests of a Keyed, Appearance-Based 3D Object Recognition System
UR > CS > Research > Vision > Publications > Large-Scale Tests of a Keyed, Appearance-Based 3D Object Recognition System
@Article{Nelson:98,
  author = 	 {Randal C. Nelson and Andrea Selinger},
  title = 	 {Large-Scale Tests of a Keyed, Appearance-Based 3D Object Recognition System},
  journal = 	 {Vision Research special issue on computational vision},
  year = 	 {1998},
  volume = 	 {38},
  number = 	 {15-16},
  month = 	 {August},
  abstract =     { We describe and analyze an appearance­based 3­D object recognition system that avoids some
of the problems of previous appearance­based schemes. We describe various large­scale per­
formance tests and report good performance for full­sphere/hemisphere recognition of up to
24 complex, curved objects, robustness against clutter and occlusion, and some intriguing
generic recognition behavior. We also establish a protocol that permits performance in the
presence of quantifiable amounts of clutter and occlusion to be predicted on the basis of simple
score statistics derived from clean test images and pure clutter images.  }
}