Maximally stable local description for scale selection

Gyuri Dorkó 1 Cordelia Schmid 1, *
* Auteur correspondant
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation. The technique performs scale selection based on a region descriptor, here SIFT, and chooses regions for which this descriptor is maximally stable. Maximal stability is obtained, when the difference between descriptors extracted for consecutive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Affine invariance is achieved by an integrated affine adaptation process based on the second moment matrix. An experimental evaluation compares our detectors to Harris-Laplace and the Laplacian in the context of image matching as well as of category and texture classification. The comparison shows the improved performance of our detector.
Type de document :
Communication dans un congrès
European Conference on Computer Vision (ECCV '06), May 2006, Graz, Austria. Springer-Verlag, 3954, pp.504--516, 2006, Lecture Notes in Computer Science (LNCS). 〈http://springerlink.metapress.com/content/0711717616n6x75g/〉. 〈10.1007/11744085_39〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548588
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:36
Dernière modification le : mercredi 11 avril 2018 - 01:53:06
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:21:58

Fichier

dorkoschmid_eccv06_MaxStableLo...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Gyuri Dorkó, Cordelia Schmid. Maximally stable local description for scale selection. European Conference on Computer Vision (ECCV '06), May 2006, Graz, Austria. Springer-Verlag, 3954, pp.504--516, 2006, Lecture Notes in Computer Science (LNCS). 〈http://springerlink.metapress.com/content/0711717616n6x75g/〉. 〈10.1007/11744085_39〉. 〈inria-00548588〉

Partager

Métriques

Consultations de la notice

220

Téléchargements de fichiers

213