Boosted kernel for image categorization

Alexis Lechervy 1 Philippe-Henri Gosselin 1 Frédéric Precioso 2
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
2 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe KEIA
SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : Recent machine learning techniques have demonstrated their capability for identifying image categories using image features. Among these techniques, Support Vector Machines (SVM) present good results for example in Pascal Voc challenge 2011 [8], particularly when they are associated with a kernel function [28, 35]. However, nowadays image categorization task is very challenging owing to the sizes of benchmark datasets and the number of categories to be classified. In such a context, lot of effort has to be put in the design of the kernel functions and underlying semantic features. In the following of the paper we call semantic features the features describing the (semantic) content of an image. In this paper, we propose a framework to learn an effective kernel function using the Boosting paradigm to linearly combine weak kernels. We then use a SVM with this kernel to categorize image databases. More specifically, this method create embedding functions to map images in a Hilbert space where they are better classified. Furthermore, our algorithm benefits from boosting process to learn this kernel with a complexity linear with the size of the training set. Experiments are carried out on popular benchmarks and databases to show the properties and behavior of the proposed method. On the PASCAL VOC2006 database, we compare our method to simple early fusion, and on the Oxford Flowers databases we show that our method outperforms the best Multiple Kernel Learning (MKL) techniques of the literature.
Type de document :
Article dans une revue
Multimedia Tools and Applications, Springer Verlag, 2013
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00799068
Contributeur : Philippe-Henri Gosselin <>
Soumis le : lundi 11 mars 2013 - 14:51:17
Dernière modification le : mardi 12 décembre 2017 - 16:08:09
Document(s) archivé(s) le : lundi 17 juin 2013 - 11:37:55

Fichier

lechervy13mtap.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00799068, version 1

Collections

Citation

Alexis Lechervy, Philippe-Henri Gosselin, Frédéric Precioso. Boosted kernel for image categorization. Multimedia Tools and Applications, Springer Verlag, 2013. 〈hal-00799068〉

Partager

Métriques

Consultations de la notice

269

Téléchargements de fichiers

112