Détail de l'auteur
Auteur Jianchao Fan |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Deep supervised and contractive neural network for SAR image classification / Jie Geng in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)
[article]
Titre : Deep supervised and contractive neural network for SAR image classification Type de document : Article/Communication Auteurs : Jie Geng, Auteur ; Hongyu Wang, Auteur ; Jianchao Fan, Auteur ; Xiaorui Ma, Auteur Année de publication : 2017 Article en page(s) : pp 2442 - 2459 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] algorithme Graph-Cut
[Termes IGN] analyse discriminante
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] filtre de déchatoiement
[Termes IGN] filtre de Gabor
[Termes IGN] image radar moirée
[Termes IGN] matrice de co-occurrence
[Termes IGN] niveau de gris (image)Résumé : (Auteur) The classification of a synthetic aperture radar (SAR) image is a significant yet challenging task, due to the presence of speckle noises and the absence of effective feature representation. Inspired by deep learning technology, a novel deep supervised and contractive neural network (DSCNN) for SAR image classification is proposed to overcome these problems. In order to extract spatial features, a multiscale patch-based feature extraction model that consists of gray level-gradient co-occurrence matrix, Gabor, and histogram of oriented gradient descriptors is developed to obtain primitive features from the SAR image. Then, to get discriminative representation of initial features, the DSCNN network that comprises four layers of supervised and contractive autoencoders is proposed to optimize features for classification. The supervised penalty of the DSCNN can capture the relevant information between features and labels, and the contractive restriction aims to enhance the locally invariant and robustness of the encoding representation. Consequently, the DSCNN is able to produce effective representation of sample features and provide superb predictions of the class labels. Moreover, to restrain the influence of speckle noises, a graph-cut-based spatial regularization is adopted after classification to suppress misclassified pixels and smooth the results. Experiments on three SAR data sets demonstrate that the proposed method is able to yield superior classification performance compared with some related approaches. Numéro de notice : A2017-176 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2645226 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2645226 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84748
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2442 - 2459[article]