HAL - INRIA :: [inria-00548231, version 1] Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

inria-00548231, version 1

Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

Svetlana Lazebnik ¹, Cordelia Schmid () ², Jean Ponce () ¹

9th IEEE International Conference on Computer Vision (ICCV '03) 1 (2003) 649--655

Abstract: We present a framework for texture recognition based on local affine-invariant descriptors and their spatial layout. At modelling time, a generative model of local descriptors is learned from sample images using the EM algorithm. The EM framework allows the incorporation of unsegmented multitexture images into the training set. The second modelling step consists of gathering co-occurrence statistics of neighboring descriptors. At recognition time, initial probabilities computed from the generative model are refined using a relaxation step that incorporates co-occurrence statistics. Performance is evaluated on images of an indoor scene and pictures of wild animals.

1: The Beckman Institute for Advanced Science and Technology (Beckman Institute)
University of Illinois
2: MOVI (IMAG-INRIA Rhône-Alpes / GRAVIR)
INRIA – CNRS : FR71 – CNRS : UMR5527 – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)

inria-00548231, version 1
http://hal.inria.fr/inria-00548231
oai:hal.inria.fr:inria-00548231
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 13:52:32
Updated on: Monday, 20 December 2010 13:59:02

See detailed view

Associated documents

PDF :

DOI: 10.1109/ICCV.2003.1238409

Full text from publisher

Export

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00548231"><analytic>
<author><persName><forename>Svetlana</forename><surname>Lazebnik</surname></persName>
<affiliation>
<orgName type="laboratory">Beckman Institute</orgName>
<orgName type="team">The Beckman Institute for Advanced Science and Technology</orgName>
<country>US</country>
<orgName type="institution">University of Illinois</orgName>
</affiliation>
</author>
<author><persName><forename>Cordelia</forename><surname>Schmid</surname></persName>
<affiliation>
<orgName type="laboratory">IMAG-INRIA Rhône-Alpes / GRAVIR</orgName>
<orgName type="team">MOVI</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Jean</forename><surname>Ponce</surname></persName>
<affiliation>
<orgName type="laboratory">Beckman Institute</orgName>
<orgName type="team">The Beckman Institute for Advanced Science and Technology</orgName>
<country>US</country>
<orgName type="institution">University of Illinois</orgName>
</affiliation>
</author>
<title type="main" level="a">Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition</title></analytic><monogr><meeting>9th IEEE International Conference on Computer Vision (ICCV '03)</meeting><imprint><publisher>IEEE Computer society</publisher><pubPlace><settlement>nice</settlement><country>France</country></pubPlace><biblScope type="publicationDate">2003-00-00</biblScope><biblScope type="vol">1</biblScope><biblScope type="pp">649--655</biblScope></imprint></monogr><idno type="doi">10.1109/ICCV.2003.1238409</idno><idno type="HALid">http://hal.inria.fr/inria-00548231</idno><idno type="HALFile">http://hal.inria.fr/inria-00548231/PDF/0649_lazebnik.pdf</idno></biblStruct>
</listBibl>
</listBibl>