Centre de documentation
scientifique

Dépouillements

Spectral-spatial classification of hyperspectral images using wavelet transform and hidden Markov random fields / Elham Kordi Ghasrodashti in Geocarto international, vol 33 n° 8 (August 2018)  

Public [article]  inGeocarto international > vol 33 n° 8 (August 2018) . - pp 771 - 790 Titre : Spectral-spatial classification of hyperspectral images using wavelet transform and hidden Markov random fields Type de document : Article/Communication Auteurs : Elham Kordi Ghasrodashti, Auteur ; Mohammad Sadegh Helfroush, Auteur ; Habibollah Danyali, Auteur Année de publication : 2018 Article en page(s) : pp 771 - 790 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] champ aléatoire de Markov [Termes IGN] image hyperspectrale [Termes IGN] régularisation [Termes IGN] transformation en ondelettes Résumé : (Auteur) This paper proposes a spectral–spatial method for classification of hyperspectral images. The proposed method, called SSC, consists of two steps. In the first step, to overcome the computation complexity, a wavelet-based classifier is designed. In the second step, to enhance the classification accuracy, a novel hidden Markov random field called NHMRF technique in spatial domain is suggested. In NHMRF, we convert two-dimensional energies of traditional hidden Markov random field to three-dimensional energies and then we apply edge preserving regularization terms on each two-dimensional energy of this cube. The class label of each test pixel is fixed based on minimum three-dimensional energy achieved by edge preserving regularization terms. Experimental results show that the classification accuracy of the proposed approach based on three-dimensional energies and edge preserving regularization terms is effectively improved in comparison with the state-of-the-art methods. Numéro de notice : A2018-335 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2017.1303087 Date de publication en ligne : 27/03/2017 En ligne : https://doi.org/10.1080/10106049.2017.1303087 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90533 [article]