Beyond bags of features: spatial pyramid matching for recognizing natural scene categories - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

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

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.
Fichier principal
Vignette du fichier
cvpr06_lana.pdf (1.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00548585 , version 1 (20-12-2010)

Identifiers

Cite

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. pp.2169 - 2178, ⟨10.1109/CVPR.2006.68⟩. ⟨inria-00548585⟩
5227 View
14314 Download

Altmetric

Share

Gmail Facebook X LinkedIn More