Hamming embedding and weak geometric consistency for large scale image search - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Hamming embedding and weak geometric consistency for large scale image search

Hervé Jégou
  • Fonction : Auteur
  • PersonId : 833473
Matthijs Douze
  • Fonction : Auteur
  • PersonId : 843109
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

This paper improves recent methods for large scale image search. State-of-the-art methods build on the bag-of-features image representation. We, first, analyze bag-of-features in the framework of approximate nearest neighbor search. This shows the sub-optimality of such a representation for matching descriptors and leads us to derive a more precise representation based on 1) Hamming embedding (HE) and 2) weak geometric consistency constraints (WGC). HE provides binary signatures that refine the matching based on visual words. WGC filters matching descriptors that are not consistent in terms of angle and scale. HE and WGC are integrated within the inverted file and are efficiently exploited for all images, even in the case of very large datasets. Experiments performed on a dataset of one million of images show a significant improvement due to the binary signature and the weak geometric consistency constraints, as well as their efficiency. Estimation of the full geometric transformation, i.e., a re-ranking step on a short list of images, is complementary to our weak geometric consistency constraints and allows to further improve the accuracy.
Fichier principal
Vignette du fichier
jegou_hewgc08.pdf (404.54 Ko) Télécharger le fichier
Vignette du fichier
wgc.jpg (24.56 Ko) Télécharger le fichier
hewgc-slides.pdf (6.98 Mo) Télécharger le fichier
jegou_hewgc_poster.pdf (70.22 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre
Format : Autre

Dates et versions

inria-00316866 , version 1 (15-03-2011)

Identifiants

Citer

Hervé Jégou, Matthijs Douze, Cordelia Schmid. Hamming embedding and weak geometric consistency for large scale image search. ECCV 2008 - 10th European Conference on Computer Vision, Oct 2008, Marseille, France. pp.304-317, ⟨10.1007/978-3-540-88682-2_24⟩. ⟨inria-00316866⟩
5611 Consultations
4224 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More