Unsupervised spectral-spatial classification of hyperspectral imagery using real and complex features and generalized histograms

Abstract

ABSTRACT In this work, we stud y unsupervised classification algorithms for hypersp ectral images based on band-by-band scalar histograms and vector-valued generali zed histograms, obtained by vector qua ntization. The corresponding histograms are compared by dissimilarity metrics such as the chi-squa re, Kolmogorov-Smirnorv, and earth mover’s distances. The histograms are constructed from homogeneous regions in th e images identified by a pre-segmentation algorithm and distance metrics between pixels. We compare the traditional spectral-only segmentation algorithms C-means and ISODATA, versus spectral-spatial segmentation algorithms such as unsupervised ECHO and a novel segmentation algorithm based on scale-space concepts. We also evaluate the use of complex features consisting of the real spectrum and its derivative as the imaginary part. The comparison between the different segmenta tion algorithms and distance metrics is based on their unsupervised classification accuracy using three real hyperspectral images with known ground truth. Keywords: Unsupervised classification, genera lized histograms, earth mover’s dist ance, hyperspectral imaging, scale-space, complex features, geometric PDEs.