Discriminative Feature Fusion for Image Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Discriminative Feature Fusion for Image Classification

Elisa Fromont
Damien Muselet
Marc Sebban

Résumé

Bag-of-words-based image classification approaches mostly rely on low level local shape features. However, it has been shown that combining multiple cues such as color, texture, or shape is a challenging and promising task which can improve the classification accuracy. Most of the state-of-the-art feature fusion methods usually aim to weight the cues without considering their statistical dependence in the application at hand. In this paper, we present a new logistic regression-based fusion method, called LRFF, which takes advantage of the different cues without being tied to any of them. We also design a new marginalized kernel by making use of the output of the regression model. We show that such kernels, surprisingly ignored so far by the computer vision community, are particularly well suited to achieve image classification tasks. We compare our approach with existing methods that combine color and shape on three datasets. The proposed learning based feature fusion process clearly outperforms the state-of-the art fusion methods for image classification.
Fichier principal
Vignette du fichier
CVPR2012.pdf (226.5 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00690244 , version 1 (09-01-2015)

Identifiants

  • HAL Id : hal-00690244 , version 1

Citer

Basura Fernando, Elisa Fromont, Damien Muselet, Marc Sebban. Discriminative Feature Fusion for Image Classification. Computer Vision and Pattern Recognition, Jun 2012, Rhode Island, United States. pp.3434-3441. ⟨hal-00690244⟩
2669 Consultations
456 Téléchargements

Partager

Gmail Facebook X LinkedIn More