Advertisement

Neural network based learning of local compatibilities for segment grouping

  • D. Riviére
  • J. F. Mangin
  • J. M. Martinez
  • F. Chavand
  • V. Frouin
Learning Methodologies
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)

Abstract

This paper addresses the automatic inference of a Gibbs distribution dedicated to segment grouping through relaxation labeling. The behavior of this method is studied through the detection of a road-like network from a noisy set of segments extracted from an image during a preprocessing step. Linking segments are added to this set to recover lost road parts. The whole segment set is organized in a relational graph and the road network restoration is modeled as a labeling process. The solution is defined as the labeling maximizing a Gibbs distribution constructed from a set of local costs computed for each graph clique. These cost functions, corresponding to interaction potentials, are learned automatically using multi-layer perceptrons. Supervised learning is performed over a training data set using only binary teaching output, “good” or “bad” configuration example. Several neural networks are used to overcome the problem of the variable complexity of clique configurations.

Keywords

Road Network Gibbs Distribution Stage Learning Markovian Random Field Model Optimal Label 
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.
    S. Geman and D. Geman. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images. IEEE PAMI, 6:721–741, 1984.Google Scholar
  2. 2.
    I.Y. Kim and H.S. Yang. Efficient image labeling based on Markov random field and error backpropagation network. Pattern Recognition, 26(11):1695–1707, 1993.CrossRefGoogle Scholar
  3. 3.
    J. Kittler and J. Illingworth. Relaxation labeling algorithms-a review. Image Vision Comput., 3(4):206–216, 1985.CrossRefGoogle Scholar
  4. 4.
    A. Manceaux-Demiau, J.-F. Mangin, J. Régis, O. Pizzato, and V. Frouin. Differential features of cortical folds. CVRMed-MRCAS'97 LNCS 1205, Springer Verlag, pages 439–448, 1997.Google Scholar
  5. 5.
    J.-F. Mangin, J. Régis., I. Bloch, V. Frouin, Y. Samson, and J. Lopez-Krahe. A MRF based random graph medelling the human cortical topography. CVRMed'95, LNCS 905, Springer, pages 177–183, 1995.Google Scholar
  6. 6.
    W. S. McCulloch and W. A. Pitts. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5:115–133, 1943.Google Scholar
  7. 7.
    F. Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65:386–408, 1958.PubMedGoogle Scholar
  8. 8.
    F. Tupin, H. Maitre, J.-F. Mangin, J.-M. Nicolas, and E. Pechersky. Linear feature detection on SAR images: Application to the road network. IEEE Geoscience and Remote Sensing, in press, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • D. Riviére
    • 1
    • 2
  • J. F. Mangin
    • 1
  • J. M. Martinez
    • 2
  • F. Chavand
    • 3
  • V. Frouin
    • 1
  1. 1.Service Hospitalier Frédéric JoliotCommissariat á l'Energie AtomiqueOrsayFrance
  2. 2.Service d'Etudes des Réacteurs et de Mathématiques AppliquéesCommissariat á l'Energie AtomiqueSaclayFrance
  3. 3.Université d'Evry CEMIF Systémes complexesEvryFrance

Personalised recommendations