Optimal models for visual recognition

  • Matevž Kovačič
  • Bojan Kverh
  • Franc Solina
Conference paper
Part of the Advances in Computing Science book series (ACS)


Over the years building models of objects from sensory data has been tackled in various ways. Following [1], model based recognition methods are divided into graph theoretic and non graph theoretic. Graph theoretic methods use graphs as a representation for objects and scenes. An object is divided into parts. Nodes of a graph that describes an object characterize the parts of the object and arcs of the graph represent spatial relations among parts of the object. Recognition of an object in the scene is performed as search for a subgraph isomorphism between the scene graph and each of the model graphs. In non graph theoretic methods, local features are used to describe the object. Grimson and Lozano-Peres [3], used a constrained tree search to efficiently coordinate values of point features and surface normals in models to those found in the scenes.


Line Segment Minimum Description Length Subgraph Isomorphism Scene Graph Minimum Description Length Principle 
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.


  1. [1]
    R. T. Chin and C. R. Dyer. Model-based recognition in robotic vision. ACM Computing Surveys, 18: 67–108, March 1986.CrossRefGoogle Scholar
  2. [2]
    P. Fua and A. J. Hanson. Objective functions for feature discrimination. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pages 1596–1602, Detroit, MI, 1989.Google Scholar
  3. [3]
    E. Grimson and T. Lozano-Perez. Model-based recognition and localization from sparse range and tactile data. International Journal of Robotics, 18: 67108, March 1986.Google Scholar
  4. [4]
    J. Hochberg. Perceptual Organization, chapter Levels of Perceptual Organization, pages 255–276. Lawrence Erlbaum Associates, New Jersey, 1981.Google Scholar
  5. [5]
    K. C. Keeler. Map representations and optimal encoding for image segmentation. Technical Report CICS-TH-292, Center for Intelligent Control Systems, March 1991.Google Scholar
  6. [6]
    R. E. Krichevsky and V. K. Trofimov. The performance of universal coding. IEEE Transactions on Information Theory, IT-27: 199–207, 1981.Google Scholar
  7. [7]
    Y. G. Leclerc. Constructing simple stable descriptions for image partitioning. International Journal of Computer Vision, 3: 73–102, 1989.CrossRefGoogle Scholar
  8. [8]
    M. Li and P. Vitanyi. An introduction to Kolmogorov complexity and its applications. Springer-Verlag, New York, 1993.MATHGoogle Scholar
  9. [9]
    S. Muggleton. Course on Inductive Logic Programming, 1993.Google Scholar
  10. [10]
    A. P. Pentland. Part segmentation for object recognition. Neural Computation, 1: 82–91, 1989.CrossRefGoogle Scholar
  11. [11]
    M. Pilu and R.B. Fisher. Recognition of geons by parametrically deformable contour models. In R.Cipolla and B.Buxton, editors, Fourth European Conference on Computer Vision, volume I of Lecture Notes in Computer Science, Berlin, April 1996. Springer-Verlag.Google Scholar
  12. [12]
    J. Rissanen. Universal coding, information, prediction, and estimation. IEEE Transactions on Information Theory, 30 (4): 629–636, 1984.MathSciNetMATHCrossRefGoogle Scholar
  13. [13]
    A. Rosenfeld and A. C. Kak. Digital Picture Processing, volume 2. Academic Press, Orlando, FL, 1982.Google Scholar
  14. [14]
    M. J. Silberman and J. Sklansky. Toward line detection by cluster analysis. In K. Voss, D. Chetverikov, and G. Sommer, editors, Computer Analysis of Images and Patterns, pages 117–122, Berlin, 1989. Akademie-Verlag.Google Scholar
  15. [15]
    Franc Solina and Ales Leonardis. Selective scene modeling. In Proceedings of the 11th International Conference on Pattern Recognition, pages A:8790, The Hague, The Netherlands, September 1992. IAPR, IEEE Computer Society Press.Google Scholar

Copyright information

© Springer-Verlag/Wien 1997

Authors and Affiliations

  • Matevž Kovačič
  • Bojan Kverh
  • Franc Solina

There are no affiliations available

Personalised recommendations