Morphological segmentation of hyperspectral images

Abstract : The present paper develops a general methodology for the morphological segmentation of hyperspectral images, i.e., with an important number of channels. This approach, based on watershed, is composed of a spectral classification to obtain the markers and a vectorial gradient which gives the spatial information. Several alternative gradients are adapted to the different hyperspectral functions. Data reduction is performed either by Factor Analysis or by model fitting. Image segmentation is done on different spaces: factor space, parameters space, etc. On all these spaces the spatial/spectral segmentation approach is applied, leading to relevant results on the image.
Type de document :
Article dans une revue
Image Analysis and Stereology, International Society for Stereology, 2007, 26 (3), pp.101-109. <http://www.ias-iss.org/ojs/IAS/article/view/813>. <10.5566/ias.v26.p101-109>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01220414
Contributeur : Guillaume Noyel <>
Soumis le : vendredi 18 décembre 2015 - 10:30:36
Dernière modification le : mardi 12 septembre 2017 - 11:41:31
Document(s) archivé(s) le : samedi 19 mars 2016 - 10:40:14

Fichier

Note_Interne_N3606MM.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Copyright (Tous droits réservés)

Identifiants

Collections

Citation

Guillaume Noyel, Jesus Angulo, Dominique Jeulin. Morphological segmentation of hyperspectral images. Image Analysis and Stereology, International Society for Stereology, 2007, 26 (3), pp.101-109. <http://www.ias-iss.org/ojs/IAS/article/view/813>. <10.5566/ias.v26.p101-109>. <hal-01220414>

Partager

Métriques

Consultations de
la notice

180

Téléchargements du document

76