Skip to Main content Skip to Navigation
Conference papers

Combining Local Recognition Methods for Better Image Recognition

Bart Lamiroy 1 Patrick Gros 1 Sylvaine Picard 1
1 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 : In this paper we propose a comprehensive framework that allows existing local appearance methods to collaborate in order to overcome their mutual drawbacks. Our approach tends to use the best suited local descriptors for a recognition task, and is capable of combining evidence of different methods in the case where no clearly superior type of descriptor exists. We achieve this collaboration by locally matching geometric configurations and let each match contribute to the computation of the apparent motion between a model image and the unknown query image. We show in this paper that, if we have a set of local methods conforming to a small set of conditions, they can share information about evidence of objects in a scene. This shared evidence results in recognition performances that lie beyond the capacities of any of the currently used individual methods.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00590136
Contributor : Team Perception <>
Submitted on : Thursday, May 5, 2011 - 4:43:33 PM
Last modification on : Friday, June 26, 2020 - 4:04:03 PM
Long-term archiving on: : Saturday, August 6, 2011 - 2:35:07 AM

File

p74.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00590136, version 1

Collections

IMAG | CNRS | INRIA | UGA

Citation

Bart Lamiroy, Patrick Gros, Sylvaine Picard. Combining Local Recognition Methods for Better Image Recognition. 11th British Machine Vision Conference (BMVC '00), Sep 2000, Bristol, United Kingdom. pp.74. ⟨inria-00590136⟩

Share

Metrics

Record views

299

Files downloads

139