Parallel Techniques for Rule-Based Scene Interpretation

  • Walter F. Bischof
  • Terry Caelli
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)

Abstract

We consider a parallel, rule-based approach for learning and recognition of pattern and objects in scenes. Classification rules for pattern fragments are learned with objects presented in isolation and are based on unary features of pattern parts and binary features of part relations. These rules are then applied to scenes composed of multiple objects. We present an approach that solves, at the same time, evidence combination and consistency analysis of multiple rule instantiations. Finally, we introduce an extension of our approach to the learning of dynamic patterns.

Keywords

Cluster Tree Inductive Logic Programming Horn Clause Rule Application Pattern Fragment 
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.

References

  1. 1.
    W. F. Bischof and T. Caelli. Learning structural descriptions of patterns: A new technique for conditional clustering and rule generation. Pattern Recognition, 27:1231–1248, 1994.CrossRefGoogle Scholar
  2. 2.
    W. F. Bischof and T. Caelli. Scene understanding by rule evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19:1284–1288, 1997.CrossRefGoogle Scholar
  3. 3.
    C. Dillon and T. Caelli. Cite-scene understanding and object recognition. In T. Caelli and W. F. Bischof, editors, Machine Learning and Image Interpretation, pages 119–187. Plenum, New York, NY, 1997.Google Scholar
  4. 4.
    P. Flynn and A. K. Jain. 3D object recognition using invariant feature indexing of interpretation tables. Computer Vision, Graphics, and Image Processing, 55:119–129, 1992.MATHGoogle Scholar
  5. 5.
    L. Grewe and A. Kak. Multi-hash: Learning object attributes and hash tables for fast 3-d object recognition. In K. Ikeuchi and M. Veloso, editors, Symbolic Visual Learning, pages 9–47. Oxford University Press, New York, NY, 1997.Google Scholar
  6. 6.
    K. Ikeuchi and M. Veloso, editors. Symbolic Visual Learning. Oxford University Press, New York, NY, 1997.MATHGoogle Scholar
  7. 7.
    Y. Lamdan and H. Wolfson. Geometric hasing: A general and efficient model-based recognition scheme. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 1407–1413, 1988.Google Scholar
  8. 8.
    D. G. Lowe. Three-dimensional object recognition from single two-dimensional images. Artificial Intelligence, 31:355–395, 1987.CrossRefGoogle Scholar
  9. 9.
    B. McCane and T. Caelli. Fuzzy conditional rule generation for the learning and recognition of 3d objects from 2d images. In T. Caelli and W. F. Bischof, editors, Machine Learning and Image Interpretation, pages 17–66. Plenum, New York, NY, 1997.Google Scholar
  10. 10.
    A. Pearce and T. Caelli. Relational evidence theory and interpreting schematics. In T. Caelli and W. F. Bischof, editors, Machine Learning and Image Interpretation, pages 67–118. Plenum, New York, NY, 1997.Google Scholar
  11. 11.
    J. R. Quinlan. Learning logical definitions from relations. Machine Learning, 5:239–266, 1990.Google Scholar
  12. 12.
    D. H. Wolpert. Stacked generalization. Neural Networks, 5:241–259, 1992.CrossRefGoogle Scholar
  13. 13.
    S. Zucker, E. V. Krishnamurty, and R. L. Haar. Relaxation processes for scene labeling: Convergence, speed, and stability. IEEE Transactions on Systems, Man and Cybernetics, 8:41–48, 1978.MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Walter F. Bischof
    • 1
  • Terry Caelli
    • 1
  1. 1.Department of Computing ScienceUniversity of AlbertaEdmontonCanada

Personalised recommendations