HAL - INRIA :: [inria-00548509, version 1] A maximum entropy framework for combining parts and relations for texture and object recognition

inria-00548509, version 1

A maximum entropy framework for combining parts and relations for texture and object recognition

Svetlana Lazebnik ¹, Cordelia Schmid ( Author to contact preferably ) ², Jean Ponce () ¹

Tenth IEEE International Conference on Computer Vision (ICCV '05) 1 (2005) 832 - 838

Abstract: This paper presents a probabilistic part-based approach for texture and object recognition. Textures are represented using a part dictionary found by quantizing the appearance of scale- or affine- invariant keypoints. Object classes are represented using a dictionary of composite semi-local parts, or groups of neighboring keypoints with stable and distinctive appearance and geometric layout. A discriminative maximum entropy framework is used to learn the posterior distribution of the class label given the occurrences of parts from the dictionary in the training set. Experiments on two texture and two object databases demonstrate the effectiveness of this framework for visual classification.

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

inria-00548509, version 1
http://hal.inria.fr/inria-00548509
oai:hal.inria.fr:inria-00548509
From: Team Lear <>
Submitted for: Laure BENAC <>
Submitted on: Monday, 20 December 2010 09:07:57
Updated on: Wednesday, 5 January 2011 15:01:37

See detailed view

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-00548509"><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">LEAR</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">CNRS : UMR5527</orgName>
<orgName type="institution">INRIA</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">A maximum entropy framework for combining parts and relations for texture and object recognition</title></analytic><monogr><meeting>Tenth IEEE International Conference on Computer Vision (ICCV '05)</meeting><imprint><publisher>IEEE Computer Society</publisher><pubPlace><settlement>Snowbird</settlement><country>United States</country></pubPlace><biblScope type="publicationDate">2005-00-00</biblScope><biblScope type="vol">1</biblScope><biblScope type="pp">832 - 838</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00548509</idno></biblStruct>
</listBibl>
</listBibl>