A maximum entropy framework for combining parts and relations for texture and object recognition

Svetlana Lazebnik 1 Cordelia Schmid 2, * Jean Ponce 1
* Auteur correspondant
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a probabilistic part-based approach for texture and object recognition. Textures are represented using a part dictionary found by quantizing the appearance of scale- or affine- invariant keypoints. Object classes are represented using a dictionary of composite semi-local parts, or groups of neighboring keypoints with stable and distinctive appearance and geometric layout. A discriminative maximum entropy framework is used to learn the posterior distribution of the class label given the occurrences of parts from the dictionary in the training set. Experiments on two texture and two object databases demonstrate the effectiveness of this framework for visual classification.
Type de document :
Communication dans un congrès
Tenth IEEE International Conference on Computer Vision (ICCV '05), Oct 2005, Snowbird, United States. IEEE Computer Society, 1, pp.832 - 838, 2005
Liste complète des métadonnées

https://hal.inria.fr/inria-00548509
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:07:57
Dernière modification le : mercredi 11 avril 2018 - 01:53:04

Identifiants

  • HAL Id : inria-00548509, version 1

Collections

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. A maximum entropy framework for combining parts and relations for texture and object recognition. Tenth IEEE International Conference on Computer Vision (ICCV '05), Oct 2005, Snowbird, United States. IEEE Computer Society, 1, pp.832 - 838, 2005. 〈inria-00548509〉

Partager

Métriques

Consultations de la notice

102