Pattern recognition with local invariant features

Cordelia Schmid 1, * Gyuri Dorkó 1 Svetlana Lazebnik 2 Krystian Mikolajczyk 1 Jean Ponce 2
* Auteur correspondant
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
2 Beckman Institute - The Beckman Institute for Advanced Science and Technology
Abstract : Local invariant features have shown to be very successful for recognition. They are robust to occlusion and clutter, distinctive as well as invariant to image transformations. In this chapter recent progress on local invariant features is summarized. It is explained how to extract scale and affine-invariant regions and how to obtain discriminant descriptors for these regions. It is then demonstrated that combining local features with pattern classification techniques allows for texture and category-level object recognition in the presence of varying viewpoints and background clutter.
Type de document :
Chapitre d'ouvrage
C.H. Chen and P.S.P Wang. Handbook of Pattern Recognition and Computer Vision, World Scientific, pp.71-92, 2005, 978-981-256-105-3
Liste complète des métadonnées
https://hal.inria.fr/inria-00548523
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:05
Dernière modification le : mercredi 11 avril 2018 - 01:55:58

Identifiants

  • HAL Id : inria-00548523, version 1

Collections

IMAG | INRIA | UGA

Citation

Cordelia Schmid, Gyuri Dorkó, Svetlana Lazebnik, Krystian Mikolajczyk, Jean Ponce. Pattern recognition with local invariant features. C.H. Chen and P.S.P Wang. Handbook of Pattern Recognition and Computer Vision, World Scientific, pp.71-92, 2005, 978-981-256-105-3. 〈inria-00548523〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

121

Contact


archive-ouverte@inria.fr