Skip to Main content Skip to Navigation
Book sections

A discriminative framework for texture and object recognition using local image features

Svetlana Lazebnik 1 Cordelia Schmid 2, * Jean Ponce 1
* Corresponding author
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This chapter presents an approach for texture and object recognition that uses scale- or affine-invariant local image features in combination with a discriminative classifier. Textures are represented using a visual dictionary found by quantizing appearance-based descriptors of local features. Object classes are represented using a dictionary of composite semi-local parts, or groups of nearby features 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 et. Experiments on two texture and two object databases demonstrate the effectiveness of this framework for visual classification.
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548596
Contributor : Thoth Team <>
Submitted on : Thursday, January 6, 2011 - 10:29:21 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Thursday, April 7, 2011 - 2:32:52 AM

File

sicily06a.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. A discriminative framework for texture and object recognition using local image features. Jean Ponce and Martial Hebert and Cordelia Schmid and Andrew Zisserman. Towards category-level object recognition, 4170, Springer-Verlag, pp.423--442, 2006, Lecture Notes in Computer Science (LNCS), 978-3-540-68794-8. ⟨10.1007/11957959⟩. ⟨inria-00548596⟩

Share

Metrics

Record views

474

Files downloads

910