A sparse texture representation using affine-invariant regions

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce

Research output: Contribution to journalConference article

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.

Original languageEnglish (US)
Pages (from-to)II/319-II/324
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
StatePublished - Sep 1 2003
Event2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Madison, WI, United States
Duration: Jun 18 2003Jun 20 2003

Fingerprint

Textures
Feature extraction

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

A sparse texture representation using affine-invariant regions. / Lazebnik, Svetlana; Schmid, Cordelia; Ponce, Jean.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 01.09.2003, p. II/319-II/324.

Research output: Contribution to journalConference article

@article{cbc93f3a91bf419bbb28dea34fc519e1,
title = "A sparse texture representation using affine-invariant regions",
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.",
author = "Svetlana Lazebnik and Cordelia Schmid and Jean Ponce",
year = "2003",
month = "9",
day = "1",
language = "English (US)",
volume = "2",
pages = "II/319--II/324",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - A sparse texture representation using affine-invariant regions

AU - Lazebnik, Svetlana

AU - Schmid, Cordelia

AU - Ponce, Jean

PY - 2003/9/1

Y1 - 2003/9/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0041438825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041438825&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0041438825

VL - 2

SP - II/319-II/324

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

ER -