Quantization of hyperspectral image manifold using probabilistic distances

Abstract : A technique of spatial-spectral quantization of hyperspectral images is introduced. Thus a quantized hyperspectral image is just summarized by K spectra which represent the spatial and spectral structures of the image. The proposed technique is based on α−connected components on a region adjacency graph. The main ingredient is a dissimilarity metric. In order to choose the metric that best fit the hyperspectral data manifold, a comparison of different probabilistic dissimilarity measures is achieved.
Type de document :
Communication dans un congrès
Nielsen F.; Barbaresco F. International Conference on Networked Geometric Science of Information, Oct 2015, Palaiseau, France. Geometric Science of Information, 9389, 2016, Lecture Notes in Computer Science. <10.1007/978-3-319-25040-3_44>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01121104
Contributeur : Gianni Franchi <>
Soumis le : vendredi 27 février 2015 - 14:17:47
Dernière modification le : mardi 12 septembre 2017 - 11:41:19
Document(s) archivé(s) le : jeudi 28 mai 2015 - 10:16:46

Fichier

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

Identifiants

Collections

Citation

Gianni Franchi, Jesus Angulo. Quantization of hyperspectral image manifold using probabilistic distances. Nielsen F.; Barbaresco F. International Conference on Networked Geometric Science of Information, Oct 2015, Palaiseau, France. Geometric Science of Information, 9389, 2016, Lecture Notes in Computer Science. <10.1007/978-3-319-25040-3_44>. <hal-01121104>

Partager

Métriques

Consultations de
la notice

379

Téléchargements du document

125