Approximate Image Matching using Strings of Bag-of-Visual Words Representation

Abstract : The Spatial Pyramid Matching approach has become very popular to model images as sets of local bag-of words. The image comparison is then done region-by-region with an intersection kernel. Despite its success, this model presents some limitations: the grid partitioning is predefined and identical for all images and the matching is sensitive to intra- and inter-class variations. In this paper, we propose a novel approach based on approximate string matching to overcome these limitations and improve the results. First, we introduce a new image representation as strings of ordered bag-of-words. Second, we present a new edit distance specifically adapted to strings of histograms in the context of image comparison. This distance identifies local alignments between subregions and allows to remove sequences of similar subregions to better match two images. Experiments on 15 Scenes and Caltech 101 show that the proposed approach outperforms the classical spatial pyramid representation and most existing concurrent methods for classification presented in recent years.
Type de document :
Communication dans un congrès
International Conference on Computer Vision Theory and Applications (VISAPP 2014), Jan 2014, Lisbon, Portugal. pp.345-353, 2014, 〈10.5220/0004676803450353〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal-ujm.archives-ouvertes.fr/ujm-01004415
Contributeur : Christophe Ducottet <>
Soumis le : mercredi 11 juin 2014 - 12:39:27
Dernière modification le : jeudi 11 janvier 2018 - 06:20:35
Document(s) archivé(s) le : jeudi 11 septembre 2014 - 12:15:32

Fichier

Nguyen2014Approximate.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Hong-Thinh Nguyen, Cécile Barat, Christophe Ducottet. Approximate Image Matching using Strings of Bag-of-Visual Words Representation. International Conference on Computer Vision Theory and Applications (VISAPP 2014), Jan 2014, Lisbon, Portugal. pp.345-353, 2014, 〈10.5220/0004676803450353〉. 〈ujm-01004415〉

Partager

Métriques

Consultations de la notice

358

Téléchargements de fichiers

296