Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

Svetlana Lazebnik 1 Cordelia Schmid 2 Jean Ponce 1
2 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We present a framework for texture recognition based on local affine-invariant descriptors and their spatial layout. At modelling time, a generative model of local descriptors is learned from sample images using the EM algorithm. The EM framework allows the incorporation of unsegmented multitexture images into the training set. The second modelling step consists of gathering co-occurrence statistics of neighboring descriptors. At recognition time, initial probabilities computed from the generative model are refined using a relaxation step that incorporates co-occurrence statistics. Performance is evaluated on images of an indoor scene and pictures of wild animals.
Type de document :
Communication dans un congrès
9th IEEE International Conference on Computer Vision (ICCV '03), Oct 2003, nice, France. IEEE Computer society, 1, pp.649--655, 2003, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1238409〉. 〈10.1109/ICCV.2003.1238409〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548231
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 13:52:32
Dernière modification le : mercredi 11 avril 2018 - 01:53:57
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:44:51

Fichier

0649_lazebnik.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition. 9th IEEE International Conference on Computer Vision (ICCV '03), Oct 2003, nice, France. IEEE Computer society, 1, pp.649--655, 2003, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1238409〉. 〈10.1109/ICCV.2003.1238409〉. 〈inria-00548231〉

Partager

Métriques

Consultations de la notice

436

Téléchargements de fichiers

257