Previous Work

  • Mark R. Stevens
  • J. Ross Beveridge
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 589)


In the purest sense, model-based recognition uses stored information about an object’s shape and/or appearance to determine the orientation and position of that object in an image. Once the pose of the object has been recovered, qualitative measurements are made to support or refute the belief that the object is actually present in the scene at the hypothesized location. Typically, a set of sequential steps, referred to as a pipeline, are used in the model-based recognition paradigm.


Object Recognition Model Feature Training Image Data Feature Integrate Graphic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Mark R. Stevens
    • 1
  • J. Ross Beveridge
    • 2
  1. 1.Worcester Polytechnic InstituteUSA
  2. 2.Colorado State UniversityUSA

Personalised recommendations