Saliency in spectral images

Abstract : Even though the study of saliency for color images has been thoroughly investigated in the past, very little attention has been given to datasets that cannot be displayed on traditional computer screens such as spectral images. Nevertheless, more than a means to predict human gaze, the study of saliency primarily allows for measuring infor- mative content. Thus, we propose a novel approach for the computation of saliency maps for spectral images. Based on the Itti model, it in- volves the extraction of both spatial and spectral features, suitable for high dimensionality images. As an application, we present a comparison framework to evaluate how dimensionality reduction techniques convey information from the initial image. Results on two datasets prove the efficiency and the relevance of the proposed approach.
Type de document :
Communication dans un congrès
Springer-Verlag. Scandinavian Conference on Image Analysis, May 2011, Ystad Saltsjöbad, Sweden. IAPR, pp.114-123, 2011
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-00637924
Contributeur : Alamin Mansouri <>
Soumis le : jeudi 3 novembre 2011 - 11:55:59
Dernière modification le : jeudi 3 novembre 2011 - 14:09:07
Document(s) archivé(s) le : samedi 4 février 2012 - 02:25:12

Fichier

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

Identifiants

  • HAL Id : hal-00637924, version 1

Collections

Citation

Steven Le Moan, Alamin Mansouri, Jon Yngve Hardeberg, Yvon Voisin. Saliency in spectral images. Springer-Verlag. Scandinavian Conference on Image Analysis, May 2011, Ystad Saltsjöbad, Sweden. IAPR, pp.114-123, 2011. <hal-00637924>

Partager

Métriques

Consultations de
la notice

196

Téléchargements du document

105