Oral Presentations: Applications Image Processing Applications

Artificial Neural Networks — ICANN 96

Volume 1112 of the series Lecture Notes in Computer Science pp 251-256


Comparison of view-based object recognition algorithms using realistic 3D models

  • V. BlanzAffiliated withMax-Planck-Institut für biologische KybernetikAT&T Bell Laboratories
  • , B. SchölkopfAffiliated withMax-Planck-Institut für biologische KybernetikAT&T Bell Laboratories
  • , H. BülthoffAffiliated withMax-Planck-Institut für biologische Kybernetik
  • , C. BurgesAffiliated withAT&T Bell Laboratories
  • , V. VapnikAffiliated withAT&T Bell Laboratories
  • , T. VetterAffiliated withMax-Planck-Institut für biologische Kybernetik

* Final gross prices may vary according to local VAT.

Get Access


Two view-based object recognition algorithms are compared: (1) a heuristic algorithm based on oriented filters, and (2) a support vector learning machine trained on low-resolution images of the objects. Classification performance is assessed using a high number of images generated by a computer graphics system under precisely controlled conditions. Training- and test-images show a set of 25 realistic three-dimensional models of chairs from viewing directions spread over the upper half of the viewing sphere. The percentage of correct identification of all 25 objects is measured.