Advertisement

Probabilistic Hypothesis Verification

  • Dietrich Büsching
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Abstract

We describe a method for hypothesis verification for view-based recognition using Bayes rule. For feature positions we assume conditional densities which are based on the observation that deviations in the relative position of feature points increase with the distance of feature points. We advocate the use of curve segments with constant sign of curvature instead of circular or elliptical arc segments. Our approach is validated with real and artificial data of mostly curved objects.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Büsching, D.: Verteilte Generierung von Objektmodellen. PhD Thesis (in German, to appear ), TU München, 1998.zbMATHGoogle Scholar
  2. 2.
    Grimson, W.E.L.: Object Recognition by Computer, MIT Press, 1990.Google Scholar
  3. 3.
    Lavallee, S., Szeliski, R.: Recovering the position and orientation of free-form objects from image contours using 3D distance maps. IEEE Trans. Pattern Analysis and Machine Intelligence, 17, 4, 378–390, 1995.CrossRefGoogle Scholar
  4. 4.
    Pope, A.R., Lowe, D.G.: Learning object recognition models from images. In Proc. ICCV, 296–301, 1993.Google Scholar
  5. 5.
    Pope, A.R.: Learning to recognize objects in images: acquiring and using probabilistic models of appearance. PhD thesis, University of British Columbia, 1995.Google Scholar
  6. 6.
    Rothwell, C.A., Zisserman, A., Forsysth, D., Mundy, J.: Planar Object Recognition using Projective Shape Representation. International Journal of Computer Vision, 16, 57–99, 1995.CrossRefGoogle Scholar
  7. 7.
    Wells, W.: MAP model matching. In Proc. CVPR, 486–492, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Dietrich Büsching
    • 1
    • 2
  1. 1.Forschungsgruppe BildverstehenTU MünchenMünchenGermany
  2. 2.School of Computer StudiesUniversity of LeedsLeedsUK

Personalised recommendations