Combining regions and patches for object class localization

Caroline Pantofaru 1 Gyuri Dorkó 2 Cordelia Schmid 3, * Martial Hebert 1
* Auteur correspondant
3 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 : We introduce a method for object class detection and localization which combines regions generated by image segmentation with local patches. Region-based descriptors can model and match regular textures reliably, but fail on parts of the object which are textureless. They also cannot repeatably identify interest points on their boundaries. By incorporating information from patch-based descriptors near the regions into a new feature, the Region-based Context Feature (RCF), we can address these issues. We apply Region-based Context Features in a semi-supervised learning framework for object detection and localization. This framework produces object-background segmentation masks of deformable objects. Numerical results are presented for pixel-level performance.
Type de document :
Communication dans un congrès
Conference on Computer Vision and Pattern Recognition Workshop (Beyond Patches workshop, CVPR '06), Jun 2006, New York, United States. IEEE Computer Society, pp.23, 2006, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1640462〉. 〈10.1109/CVPRW.2006.57〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548581
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:22
Dernière modification le : mercredi 11 avril 2018 - 01:56:25
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:19:50

Fichier

pantofarudorkoschmidhebert_bey...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Caroline Pantofaru, Gyuri Dorkó, Cordelia Schmid, Martial Hebert. Combining regions and patches for object class localization. Conference on Computer Vision and Pattern Recognition Workshop (Beyond Patches workshop, CVPR '06), Jun 2006, New York, United States. IEEE Computer Society, pp.23, 2006, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1640462〉. 〈10.1109/CVPRW.2006.57〉. 〈inria-00548581〉

Partager

Métriques

Consultations de la notice

284

Téléchargements de fichiers

178