A hierarchical Markov random field model and multi-temperature annealing for parallel image classification

Zoltan Kato 1 Marc Berthod 1 Josiane Zerubia 1
1 PASTIS - Scene Analysis and Symbolic Image Processing
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : In this report, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. It is well known that multigrid methods can improve significantly the convergence rate and the quality of the final results of iterative relaxation techniques. First, we present a classical multiscale model which consists of a label pyramid and a whole observation field. The potential functions of coarser grids are derived by simple computations. The optimization problem is first solved at the higher scale by a parallel relaxation algorithm, then the next lower scale is initialized by a projection of the result. Second, we propose a hierarchical Markov Random Field model based on this classical model. We introduce new interactions between neighbor levels in the pyramid. It can also be seen as a way to incorporate cliques with far apart sites for a reasonable price. This model results in a relaxation algorithm with a new annealing scheme: The Multi-Temperature Annealing (MTA) scheme, which consists of associating higher temperatures to higher levels, in order to be less sensitive to local minima at coarser grids. The convergence to the global optimum is proved by a generalisation of the annealing theorem of Geman and Geman.
Type de document :
[Research Report] RR-1938, INRIA. 1993
Liste complète des métadonnées

Contributeur : Rapport de Recherche Inria <>
Soumis le : mercredi 24 mai 2006 - 16:12:08
Dernière modification le : jeudi 11 janvier 2018 - 16:38:53
Document(s) archivé(s) le : mardi 12 avril 2011 - 18:43:56



  • HAL Id : inria-00074736, version 1



Zoltan Kato, Marc Berthod, Josiane Zerubia. A hierarchical Markov random field model and multi-temperature annealing for parallel image classification. [Research Report] RR-1938, INRIA. 1993. 〈inria-00074736〉



Consultations de la notice


Téléchargements de fichiers