Semi-iterative Inferences with Hierarchical Energy-Based Models for Image Analysis

  • Annabelle Chardin
  • Patrick Pérez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1654)


This paper deals with hierarchical Markov Random Field models. We propose to introduce newhi erarchical models based on a hybrid structure which combines a spatial grid of a reduced size at the coarsest level with sub-trees appended below it, down to the finest level. These models circumvent the algorithmic drawbacks of grid-based models (computational load and/or great dependance on the initialization) and the modeling drawbacks of tree-based approaches (cumbersome and somehowa rtificial structure). The hybrid structure leads to algorithms that mix a non-iterative inference on sub-trees with an iterative deterministic inference at the top of the structure. Experiments on synthetic images demonstrate the gains provided in terms of both computational efficiency and quality of results. Then experiments on real satellite spot images illustrate the ability of hybrid models to perform efficiently the multispectral image analysis.


Hierarchical Model Hybrid Structure Coarse Level Synthetic Image Multigrid Approach 
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.
    L. E. Baum, T. Petrie, G. Soules, and N. Weiss. A maximization technique occuring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat., Vol 41: pp. 164–171, 1970.zbMATHMathSciNetCrossRefGoogle Scholar
  2. 2.
    J. Besag. Spatial interaction and the statistical analysis of lattice systems. J. Royal Statist. Soc., 36, Série B:192–236, 1974.zbMATHMathSciNetGoogle Scholar
  3. 3.
    C. Bouman and B. Liu. Multiple resolution segmentation of textured images. IEEE Trans. Pattern Anal. Machine Intell., Vol. 13, No. 2: pages 99–113, Février 1991.CrossRefGoogle Scholar
  4. 4.
    C. Bouman and M. Shapiro. A multiscale random field model for Bayesian image segmentation. IEEE Trans. Image Processing, 3, No. 2:162–177, March 1994.CrossRefGoogle Scholar
  5. 5.
    B. Chalmond. An iterative Gibbsian technique for reconstruction of m-ary images. Pattern Recognition, Vol. 22, No 6: pages 747–761, 1989.CrossRefGoogle Scholar
  6. 6.
    A. Chardin and P. Pérez. Semi-iterative inference with hierarchical models. In Int. Conf. on Image Processing, pages 630–634, Chicago, USA, october 1998.Google Scholar
  7. 7.
    G. D. Forney. The Viterbi algorithm. Proc. IEEE, Vol. 13: pages 268–278, March 1973.CrossRefMathSciNetGoogle Scholar
  8. 8.
    F. Heitz, P. Pérez, and P. Bouthemy. Multiscale minimization of global energy functions in some visual recovery problems. CVGIP: Image Understanding, Vol. 59, No 1: pages 125–134, Jan. 1994.CrossRefGoogle Scholar
  9. 9.
    J-M Laferté, P. Pérez, and F. Heitz. Discrete markov image modeling and inference on the quad-tree. IEEE Trans. Image Processing, Accepted for publication, 1999.Google Scholar
  10. 10.
    M. Luettgen, W. Karl, and A. Willsky. Efficient multiscale regularization with applications to the computation of optical flow. IEEE Trans. Image Processing, 3(1):41–64, 1994.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Annabelle Chardin
    • 1
  • Patrick Pérez
    • 1
  1. 1.IRISA/INRIACampus de BeaulieuRennes cedexFrance

Personalised recommendations