An Evaluation of Divide-and-Combine Strategies for Image Categorization by Multi-Class Support Vector Machines

Abstract : Categorization of real world images without human intervention is a challenging ongoing research. The nature of this problem requires usage of multiclass classification techniques. In divide-and-combine approach, a multiclass problem is divided into a set of binary classification problems and then the binary classifications are combined to obtain multi-class classification. Our objective in this work is to compare several divide-and-combine multiclass SVM classification strategies for real world image classification. Our results show that One-against-all and One-against-one MaxWins are the most efficient methods.
Type de document :
Communication dans un congrès
Erol Gelenbe. 23rd International Symposium on Computer and Information Sciences, 2008. ISCIS '08, Oct 2008, Istanbul, Turkey. IEEE, pp.1 - 6, 2008, 〈10.1109/ISCIS.2008.4717904〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00612239
Contributeur : Hocine Cherifi <>
Soumis le : jeudi 28 juillet 2011 - 13:43:32
Dernière modification le : lundi 16 juillet 2012 - 10:52:22
Document(s) archivé(s) le : lundi 7 novembre 2011 - 11:34:04

Fichier

ISCIS08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Can Demirkesen, Hocine Cherifi. An Evaluation of Divide-and-Combine Strategies for Image Categorization by Multi-Class Support Vector Machines. Erol Gelenbe. 23rd International Symposium on Computer and Information Sciences, 2008. ISCIS '08, Oct 2008, Istanbul, Turkey. IEEE, pp.1 - 6, 2008, 〈10.1109/ISCIS.2008.4717904〉. 〈hal-00612239〉

Partager

Métriques

Consultations de
la notice

153

Téléchargements du document

135