Beyond bags of features: spatial pyramid matching for recognizing natural scene categories

Svetlana Lazebnik 1 Cordelia Schmid 2, * Jean Ponce 3
* 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 method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba's "gist" and Lowe's SIFT descriptors.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. IEEE Computer Society, pp.2169 - 2178, 2006, <http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1641019>. <10.1109/CVPR.2006.68>
Liste complète des métadonnées


https://hal.inria.fr/inria-00548585
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:26
Dernière modification le : jeudi 29 septembre 2016 - 01:26:49
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:20:38

Fichier

cvpr06_lana.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA | PSL

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. IEEE Computer Society, pp.2169 - 2178, 2006, <http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1641019>. <10.1109/CVPR.2006.68>. <inria-00548585>

Partager

Métriques

Consultations de
la notice

633

Téléchargements du document

6839