Region-Based Representation for Object Recognition by Relaxation Labelling

  • Alireza Ahmadyfard
  • Josef Kittler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


We address the problem of object recognition in computer vision. We propose an invariant representation of the model and scene in the form of Attributed Relational Graph with focus on region based measurements rather than purely interest points. This approach enhances the stability of scene image representation in the presence of noise and significant scaling. Improved solution is achieved by employing a multiple region representation at each node of the ARG.The matching of scene and model ARGs is accomplished using probabilistic relaxation that has been modified to cope with multiple scene representation. The preliminary results obtained in experiments with real data are encouraging.


Object Recognition Invariant Representation Computer Vision 


  1. 1.
    Hoover A., Goldgof D., and Bowyer K. Function from visual analysis and physical interaction: a methodology for recognition of generic classes of objects. Computer Vision and Image Understanding, 69(3):310–329, 1998.CrossRefGoogle Scholar
  2. 2.
    Rosenfeld A., Hummel R., and Zucker S. Scene labeling by relaxation operations. IEEE Transaction on system man and cybernetics, pages 420–433, 1976.Google Scholar
  3. 3.
    Dorin Comaniciu and Peter Meer. Robust analysis of feature spaces: Color image segmentation. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages 750–755, 1997.Google Scholar
  4. 4.
    Huttenlocherr D.P and Ullman S. Recognizing solid objects by alignment with an image. International Journal of Computer Vision, pages 195–212, 1990.Google Scholar
  5. 5.
    D.P. Huttenlocher and Shimon Ullman. object recognition using alignment. first international confrance of computer vision, pages 102–111, 1987.Google Scholar
  6. 6.
    Wolfson H.J. Model-based object recognition by geometric hashing. International confrence on computer vision, pages 526–536, 1990.Google Scholar
  7. 7.
    Wolfson H.J. and Lamdan Y. Geometric hashing: A general and efficient model-based recognition scheme. Second International Conference on Computer Vision, pages 238–249, 1988.Google Scholar
  8. 8.
    Kittler j. and Hancock E.R. Combination evidence in probabilistic relaxation. International Journal of Pattern Recognition and Artificial Intelligence, 3(1):29–51, 1989.CrossRefGoogle Scholar
  9. 9.
    Wong K.C., Sim H.C, and J. Kittler. Recognition of two dimensional objects based on a novel generalized hough transform method. IEEE International Conference on Image Processing, 3:376–379, 1995.CrossRefGoogle Scholar
  10. 10.
    Z. Shao and J. Kittler. Shape recognition using invariant unary and binary relations. Advances in Visual Form Analysis, pages 529–538, 1997.Google Scholar
  11. 11.
    Zhimin Shao. 3D/2D Object Recognition From Surface Patterns. PhD thesis, Center for Video,Speech and Signal Processing, 1997.Google Scholar
  12. 12.
    Christmas W.J., Kittler J., and Petrou M. Structural matching in computer vision using probabilistic relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligenc e, pages 749–764, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Alireza Ahmadyfard
    • 1
  • Josef Kittler
    • 1
  1. 1.Centre for Vision, Speech and Signal Processing, School of Electronic Engineering, Information Technology and MathematicsUniversity of SurreyGuildfordUK

Personalised recommendations