Figure-Ground Discrimination by Mean Field Annealing

Abstract : We formulate the figure-ground discrimination problem as a combinatorial optimization problem. We suggest a cost function that makes explicit a definition of shape based on interactions between image edges. These interactions have some mathematical analogy with interacting spin systems -- a model that is well suited for solving combinatorial optimization problems. We devise a mean field annealing method for finding the global minimum of such a spin system and the method successfully solves for the figure-ground problem.
Type de document :
Communication dans un congrès
G. Sandini. 2nd European Conference on Computer Vision (ECCV '92), May 1992, Santa Margherita Ligure, Italy. Springer-Verlag, 588/1992, pp.58--66, 1992, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-55426-2_7〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00590008
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:05:00
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04

Identifiants

Collections

CEA | IMAG | INRIA | UGA | DRT

Citation

Laurent Herault, Radu Horaud. Figure-Ground Discrimination by Mean Field Annealing. G. Sandini. 2nd European Conference on Computer Vision (ECCV '92), May 1992, Santa Margherita Ligure, Italy. Springer-Verlag, 588/1992, pp.58--66, 1992, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-55426-2_7〉. 〈inria-00590008〉

Partager

Métriques

Consultations de la notice

92