Graph Matching via Sequential Monte Carlo

Yumin Suh 1 Minsu Cho 2 Kyoung Mu Lee 1
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Graph matching is a powerful tool for computer vision and machine learning. In this paper, a novel approach to graph matching is developed based on the sequential Monte Carlo framework. By constructing a sequence of intermediate target distributions, the proposed algorithm sequentially performs a sampling and importance resampling to maximize the graph matching objective. Through the sequential sampling procedure, the algorithm effectively collects potential matches under one-to-one matching constraints to avoid the adverse effect of outliers and deformation. Experimental evaluations on synthetic graphs and real images demonstrate its higher robustness to deformation and outliers.
Type de document :
Communication dans un congrès
ECCV - European Conference on Computer Vision, Sep 2012, Firenze, Italy. 2012
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01064703
Contributeur : Minsu Cho <>
Soumis le : mercredi 17 septembre 2014 - 04:18:11
Dernière modification le : mardi 17 avril 2018 - 11:23:52
Document(s) archivé(s) le : jeudi 18 décembre 2014 - 10:15:49

Fichier

SMCM_ECCV2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01064703, version 1

Collections

Citation

Yumin Suh, Minsu Cho, Kyoung Mu Lee. Graph Matching via Sequential Monte Carlo. ECCV - European Conference on Computer Vision, Sep 2012, Firenze, Italy. 2012. 〈hal-01064703〉

Partager

Métriques

Consultations de la notice

179

Téléchargements de fichiers

179