HAL : hal-00612219, version 1

DOI : 10.1007/978-3-540-88458-3_68

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

Advanced Concepts for Intelligent Vision Systems, 10th International Conference, ACIVS 2008, Juan-les-Pins : France (2008)

A Comparison of Multiclass SVM Methods for Real World Natural Scenes

Can Demirkesen 1, Hocine Cherifi 1, 2

(2008)

Categorization of natural scene images into semantically meaningful categories is a challenging problem that requires usage of multiclass classification methods. Our objective in this work is to compare multiclass SVM classification strategies for this task. We compare the approaches where a multi-class classifier is constructed by combining several binary classifiers and the approaches that consider all classes at once. The first approach is generally termed as "divide-and-combine" and the second is known as "all-in-one". Our experimental results show that all-in-one SVM outperforms the other methods.

1 :	BIT lab (BIT Lab)
	Université Galatasaray
2 :	Laboratoire Electronique, Informatique et Image (Le2i)
	Université de Bourgogne – Arts et Métiers ParisTech – CNRS : UMR6306

Domaine

:

Informatique/Vision par ordinateur et reconnaissance de formes

hal-00612219, version 1

http://hal.archives-ouvertes.fr/hal-00612219

oai:hal.archives-ouvertes.fr:hal-00612219

Contributeur : Hocine Cherifi <>

Soumis le : Jeudi 28 Juillet 2011, 12:25:25

Dernière modification le : Lundi 16 Juillet 2012, 10:50:53