Efficient Matching with Invariant Local Descriptors

Roger Mohr 1 Patrick Gros 1 Cordelia Schmid 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 : We are addressing the problem of matching images of scene or of objects when a large collection of reference objects is considered. The paper addresses also the issue of dealing with illumination change and camera position changes. Our approach is firstly based on the use of invariants. Invariants have to be computed locally so that the resulting values will not affected by partial occlusion or accidental highlights. In- variants proved to be a very discriminant piece of information and stored in a hash table they allow efficient indexing of visual shape. Final recognition can be performed using simply a robust voting technique or can be improved using Bayesian decision.
Type de document :
Communication dans un congrès
Adnan Amin and Dov Dori and Pavel Pudil and Herbert Freeman. Joint IAPR International Workshops SSPR'98 and SPR'98, Aug 1998, Sydney, Australia. Springer-Verlag, 1451, pp.54--71, 1998, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/w2u72tt7m585j4hv/〉. 〈10.1007/BFb0033226〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548332
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:43:26
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Roger Mohr, Patrick Gros, Cordelia Schmid. Efficient Matching with Invariant Local Descriptors. Adnan Amin and Dov Dori and Pavel Pudil and Herbert Freeman. Joint IAPR International Workshops SSPR'98 and SPR'98, Aug 1998, Sydney, Australia. Springer-Verlag, 1451, pp.54--71, 1998, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/w2u72tt7m585j4hv/〉. 〈10.1007/BFb0033226〉. 〈inria-00548332〉

Partager

Métriques

Consultations de la notice

103