Combining Color and Shape Information for Appearance-Based Object Recognition Using Ultrametric Spin Glass-Markov Random Fields

Abstract : Shape and color information are important cues for object recognition. An ideal system should give the option to use both forms of information, as well as the option to use just one of the two. We present in this paper a kernel method that achieves this goal. It is based on results of statistical physics of disordered systems combined with Gibbs distributions via kernel functions. Experimental results on a database of 100 objects confirm the effectiveness of the proposed approach.
Type de document :
Communication dans un congrès
Seong-Whan Lee and Alessandro Verri. International Conference on Pattern Recognition with Support Vector Machines (SVM '02), Aug 2002, Niagara Falls, Canada. Springer, 2388, pp.841--847, 2002, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/k7nguyqvt9rvkwff/〉. 〈10.1007/3-540-45665-1_8〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548259
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:42:28
Dernière modification le : mardi 21 décembre 2010 - 10:35:43

Lien texte intégral

Identifiants

Citation

Barbara Caputo, Gyuri Dorkó, Heinrich Niemann. Combining Color and Shape Information for Appearance-Based Object Recognition Using Ultrametric Spin Glass-Markov Random Fields. Seong-Whan Lee and Alessandro Verri. International Conference on Pattern Recognition with Support Vector Machines (SVM '02), Aug 2002, Niagara Falls, Canada. Springer, 2388, pp.841--847, 2002, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/k7nguyqvt9rvkwff/〉. 〈10.1007/3-540-45665-1_8〉. 〈inria-00548259〉

Partager

Métriques

Consultations de la notice

20