Object Indexing is a Complex Matter

Bart Lamiroy 1 Patrick Gros 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 address de problem of algorithmic complexity relative to object recognition through indexing of local descriptors. Indeed, recent work has shown the possible advantages of these recognition techniques which are generally robust and efficient. Although they appear to be potentially very fast, our study shows that the overall complexity of the method is quadratic in the number of local descriptors per image, raising the question of the usefulness of these approaches for large indexing bases of complex images. We show, however, that a careful choice of descriptors may sufficiently reduce the inherent overhead in real applications. As a result we advance that it is more useful to use high-dimensional local descriptors which may be less discriminative, rather than lower-dimensional descriptors with a high expressive value to achieve an optimal recognition result.
Type de document :
Communication dans un congrès
Michael Frydrych and Jussi Parkkinen and Ari Visa. 10th Scandinavian Conference on Image Analysis (SCIA '97), Jun 1997, Lappeenranta, Finland. I, pp.277--283, 1997
Liste complète des métadonnées

https://hal.inria.fr/inria-00590077
Contributeur : Team Perception <>
Soumis le : jeudi 5 mai 2011 - 14:07:56
Dernière modification le : mercredi 11 avril 2018 - 01:54:13
Document(s) archivé(s) le : samedi 6 août 2011 - 02:32:38

Fichiers

lamiroy_object.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00590077, version 1

Collections

IMAG | INRIA | UGA

Citation

Bart Lamiroy, Patrick Gros. Object Indexing is a Complex Matter. Michael Frydrych and Jussi Parkkinen and Ari Visa. 10th Scandinavian Conference on Image Analysis (SCIA '97), Jun 1997, Lappeenranta, Finland. I, pp.277--283, 1997. 〈inria-00590077〉

Partager

Métriques

Consultations de la notice

111

Téléchargements de fichiers

107