a Sparse Texture Representation Using Affine-Invariant Neighborhoods Regions

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 : This paper introduces a texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and nonrigid deformations. At the feature extraction stage, a sparse set of affine-invariant local patches is extracted from the image. This spatial selection process permits the computation of characteristic scale and neighborhood shape for every texture element. The proposed texture representation is evaluated in retrieval and classification tasks using the entire Brodatz database and a collection of photographs of textured surfaces taken from different viewpoints.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548232
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 8:42:07 AM
Last modification on : Monday, August 19, 2019 - 1:40:02 PM
Long-term archiving on : Monday, March 21, 2011 - 2:45:17 AM

File

lana_cvpr03.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | INRIA | UGA

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. a Sparse Texture Representation Using Affine-Invariant Neighborhoods Regions. International Conference on Computer Vision & Pattern Recognition (CVPR '03), Jun 2003, Madison, United States. pp.319--324, ⟨10.1109/CVPR.2003.1211486⟩. ⟨inria-00548232⟩

Share

Metrics

Record views

390

Files downloads

785