Image Retrieval with Reciprocal and shared Nearest Neighbors

Agni Delvinioti 1 Hervé Jégou 1 Laurent Amsaleg 1 Michael E. Houle 2
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Content-based image retrieval systems typically rely on a similarity measure between image vector representations, such as in bag-of-words, to rank the database images in decreasing order of expected relevance to the query. However, the inherent asymmetry of k-nearest neighborhoods is not properly accounted for by traditional similarity measures, possibly leading to a loss of retrieval accuracy. This paper addresses this issue by proposing similarity measures that use neighborhood information to assess the relationship between images. First, we extend previous work on k-reciprocal nearest neighbors to produce new measures that improve over the original primary metric. Second, we propose measures defined on sets of shared nearest neighbors for re-ranking the shortlist. Both these methods are simple, yet they significantly improve the accuracy of image search engines on standard benchmark datasets.
Type de document :
Communication dans un congrès
VISAPP--International Conference on Computer Vision Theory and Applications, Jan 2014, Barcelone, Portugal. 2014
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-00907481
Contributeur : Laurent Amsaleg <>
Soumis le : jeudi 6 février 2014 - 12:02:47
Dernière modification le : jeudi 11 janvier 2018 - 06:20:10
Document(s) archivé(s) le : mardi 6 mai 2014 - 22:06:00

Fichiers

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

Identifiants

  • HAL Id : hal-00907481, version 1

Collections

Citation

Agni Delvinioti, Hervé Jégou, Laurent Amsaleg, Michael E. Houle. Image Retrieval with Reciprocal and shared Nearest Neighbors. VISAPP--International Conference on Computer Vision Theory and Applications, Jan 2014, Barcelone, Portugal. 2014. 〈hal-00907481〉

Partager

Métriques

Consultations de la notice

829

Téléchargements de fichiers

706