SPECTRAL ANALYSIS AND UNSUPERVISED SVM CLASSIFICATION FOR SKIN HYPER-PIGMENTATION CLASSIFICATION

Sylvain Prigent 1 Xavier Descombes 1 Didier Zugaj 2 Josiane Zerubia 1
1 ARIANA - Inverse problems in earth monitoring
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SIS - Signal, Images et Systèmes
2 GALDERMA R&D
Abstract : Data reduction procedures and classification via support vector machines (SVMs) are often associated with multi or hyperspectral image analysis. In this paper, we propose an automatic method with these two schemes in order to perform a classification of skin hyper-pigmentation on multi-spectral images. We propose a spectral analysis method to partition the spectrum as a tool for data reduction, implemented by projection pursuit. Once the data is reduced, an SVM is used to differentiate the pathological from the healthy areas. As SVM is a supervised classification method, we propose a spatial criterion for spectral analysis in order to perform automatic learning.
Type de document :
Communication dans un congrès
IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (Whispers), Jun 2010, Reykjavik, Iceland. 2010
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00495560
Contributeur : Sylvain Prigent <>
Soumis le : lundi 28 juin 2010 - 11:04:43
Dernière modification le : lundi 5 novembre 2018 - 15:52:01
Document(s) archivé(s) le : lundi 22 octobre 2012 - 16:30:37

Fichier

whispers2010_submission_124.pd...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00495560, version 1

Collections

UNICE | INRIA | I3S | UNIV-COTEDAZUR

Citation

Sylvain Prigent, Xavier Descombes, Didier Zugaj, Josiane Zerubia. SPECTRAL ANALYSIS AND UNSUPERVISED SVM CLASSIFICATION FOR SKIN HYPER-PIGMENTATION CLASSIFICATION. IEEE Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (Whispers), Jun 2010, Reykjavik, Iceland. 2010. 〈inria-00495560〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

357

Téléchargements de fichiers

218

Contact


archive-ouverte@inria.fr