Learning an efficient and robust graph matching procedure for specific object recognition

Abstract : We present a fast and robust graph matching approach for 2D specific object recognition in images. From a small number of training images, a model graph of the object to learn is automatically built. It contains its local keypoints as well as their spatial proximity relationships. Training is based on a selection of the most efficient subgraphs using the mutual information. The detection uses dynamic programming with a lattice and thus is very fast. Experiments demonstrate that the proposed method outperforms the specific object detectors of the state-of-the-art in realistic noise conditions.
Type de document :
Communication dans un congrès
International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. IEEE, pp.754-757, 2010, 〈10.1109/ICPR.2010.190〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01381492
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : vendredi 14 octobre 2016 - 14:46:54
Dernière modification le : jeudi 19 avril 2018 - 14:38:06

Identifiants

Citation

Jérôme Revaud, Guillaume Lavoué, Yasuo Ariki, Atilla Baskurt. Learning an efficient and robust graph matching procedure for specific object recognition. International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. IEEE, pp.754-757, 2010, 〈10.1109/ICPR.2010.190〉. 〈hal-01381492〉

Partager

Métriques

Consultations de la notice

223