Skip to Main content Skip to Navigation
Conference papers

Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

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 : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548231
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 1:52:32 PM
Last modification on : Friday, June 26, 2020 - 4:04:03 PM
Long-term archiving on: : Monday, March 21, 2011 - 2:44:51 AM

File

0649_lazebnik.pdf
Publisher files allowed on an open archive

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition. 9th IEEE International Conference on Computer Vision (ICCV '03), Oct 2003, nice, France. pp.649--655, ⟨10.1109/ICCV.2003.1238409⟩. ⟨inria-00548231⟩

Share

Metrics

Record views

659

Files downloads

838