Combining Local Recognition Methods for Better Image Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2000

Combining Local Recognition Methods for Better Image Recognition


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.
Fichier principal
Vignette du fichier
lamiroy_vision_2001.pdf (442.35 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

inria-00604483 , version 1 (01-07-2011)


  • HAL Id : inria-00604483 , version 1


Bart Lamiroy, Patrick Gros, Sylvaine Picard. Combining Local Recognition Methods for Better Image Recognition. BMVC2000 - Eleventh British Machine Vision Conference, Sep 2000, Bristol, United Kingdom. pp.74. ⟨inria-00604483⟩
307 View
147 Download


Gmail Facebook Twitter LinkedIn More