Extended Self-Dual Attribute Profiles for the Classification of Hyperspectral Images

Gabriele Cavallaro (1) , Mauro Dalla Mura (2) , Jon Atli Benediktsson (1) , Lorenzo Bruzzone (3)

1 University of Iceland [Reykjavik]
2 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
3 DISI - Department of Information Engineering and Computer Science

—In this letter, we explore the use of self-dual attribute profiles (SDAPs) for the classification of hyperspectral images. The hyperspectral data are reduced into a set of components by non-parametric weighted feature extraction (NWFE), and a morphological processing is then performed by the SDAPs separately on each of the extracted components. Since the spatial information extracted by SDAPs results in a high number of features, the NWFE is applied a second time in order to extract a fixed number of features, which are finally classified. The experiments are carried out on two hyperspectral images, and the support vector machines (SVMs) and Random Forest (RF) are used as classifiers. The effectiveness of SDAPs is assessed by comparing its results against those obtained by an approach based on extended attribute profiles (EAPs).

Mots clés: mathematical morphology; non-parametric weighted feature extraction; extended attribute profiles; Index Terms—Attribute filters; attribute profiles; self-dual attribute profiles; remote sensing

Domaines: Traitement du signal et de l'image [eess.SP]

Gabriele Cavallaro, Mauro Dalla Mura, Jon Atli Benediktsson, Lorenzo Bruzzone. Extended Self-Dual Attribute Profiles for the Classification of Hyperspectral Images. IEEE Geoscience and Remote Sensing Letters, 2015, 12 (8), pp.1690-1694. ⟨10.1109/LGRS.2015.2419629⟩. ⟨hal-01259781⟩