Spatial Weighting for Bag-of-Features - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Spatial Weighting for Bag-of-Features

Résumé

This paper presents an extension to category classification with bag-of-features, which represents an image as an orderless distribution of features. We propose a method to exploit spatial relations between features by utilizing object boundaries provided during supervised training. We boost the weights of features that agree on the position and shape of the object and suppress the weights of background features, hence the name of our method - "spatial weighting". The proposed representation is thus richer and more robust to background clutter. Experimental results show that our approach improves the results of one of the best current image classification techniques. Furthermore, we propose to apply the spatial model to object localization. Initial results are promising.
Fichier principal
Vignette du fichier
MarszalekSchmid-CVPR06-SpatialWeighting.pdf (1.21 Mo) Télécharger le fichier
Vignette du fichier
carsgraz_253_mult.png (377.03 Ko) Télécharger le fichier
MarszalekSchmid-CVPR06-SpatialWeighting-poster.pdf (961.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre

Dates et versions

inria-00548584 , version 1 (20-12-2010)

Identifiants

Citer

Marcin Marszałek, Cordelia Schmid. Spatial Weighting for Bag-of-Features. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. pp.2118--2125, ⟨10.1109/CVPR.2006.288⟩. ⟨inria-00548584⟩
113 Consultations
363 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More