Shape recognition with edge-based features

Krystian Mikolajczyk 1 Andrew Zisserman 1 Cordelia Schmid 2
2 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 describe an approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions. To this end we develop a number of novel components. First, we introduce a new edge-based local feature detector that is invariant to similarity transformations. The features are localized on edges and a neighbourhood is estimated in a scale invariant manner. Second, the neighbourhood descriptor computed for foreground features is not affected by background clutter, even if the feature is on an object boundary. Third, the descriptor generalizes Lowe's SIFT method to edges. An object model is learnt from a single training image. The object is then recognized in new images in a series of steps which apply progressively tighter geometric restrictions. A final contribution of this work is to allow sufficient flexibility in the geometric representation that objects in the same visual class can be recognized. Results are demonstrated for various object classes including bikes and rackets.
Mots-clés : LEAR LAVA
Type de document :
Communication dans un congrès
Richard Harvey and Andrew Bangham. British Machine Vision Conference (BMVC '03), Sep 2003, Norwich, United Kingdom. The British Machine Vision Association, 2, pp.779--788, 2003, 〈http://www.bmva.org/bmvc/2003/papers/paper-23-155.html〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548226
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 12:05:09
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:43:26

Fichier

mikolajczyk03a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548226, version 1

Collections

IMAG | INRIA | UGA

Citation

Krystian Mikolajczyk, Andrew Zisserman, Cordelia Schmid. Shape recognition with edge-based features. Richard Harvey and Andrew Bangham. British Machine Vision Conference (BMVC '03), Sep 2003, Norwich, United Kingdom. The British Machine Vision Association, 2, pp.779--788, 2003, 〈http://www.bmva.org/bmvc/2003/papers/paper-23-155.html〉. 〈inria-00548226〉

Partager

Métriques

Consultations de la notice

1270

Téléchargements de fichiers

886