Oriented pooling for dense and non-dense rotation-invariant features

Wan-Lei Zhao 1 Hervé Jégou 1 Guillaume Gravier 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper proposes a pooling strategy for local descriptors to produce a vector representation that is orientation-invariant yet implicitly incorporates the relative angles between features measured by their dominant orientation. This pooling is associated with a similarity metric that ensures that all the features have undergone a comparable rotation. This approach is especially effective when combined with dense oriented features, in contrast to existing methods that either rely on oriented features extracted on key points or on non-oriented dense features. The interest of our approach in a retrieval scenario is demonstrated on popular benchmarks comprising up to 1 million database images.
Type de document :
Communication dans un congrès
BMVC - 24th British Machine Vision Conference, Sep 2013, Bristol, United Kingdom. 2013
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00841590
Contributeur : Hervé Jégou <>
Soumis le : vendredi 23 août 2013 - 12:06:38
Dernière modification le : vendredi 16 novembre 2018 - 01:25:57
Document(s) archivé(s) le : jeudi 6 avril 2017 - 06:01:34

Fichier

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

Identifiants

  • HAL Id : hal-00841590, version 2

Citation

Wan-Lei Zhao, Hervé Jégou, Guillaume Gravier. Oriented pooling for dense and non-dense rotation-invariant features. BMVC - 24th British Machine Vision Conference, Sep 2013, Bristol, United Kingdom. 2013. 〈hal-00841590v2〉

Partager

Métriques

Consultations de la notice

1279

Téléchargements de fichiers

322