Spectral-Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques

• Published in: IEEE transactions on geoscience and remote sensing Vol. 47; no. 8; pp. 2973 - 2987
• Main Authors: Tarabalka, Y., Benediktsson, J.A., Chanussot, J.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied geophysics; Clustering; Clustering algorithms; Computer Science; Earth sciences; Earth, ocean, space; Exact sciences and technology; hyperspectral images; Hyperspectral imaging; Hyperspectral sensors; Image Processing; Image segmentation; Internal geophysics; majority vote; Partitioning algorithms; Pixel; Remote monitoring; segmentation; Spatial resolution; spectral-spatial classification; Support vector machine classification; Voting; algorithms; maps; data processing; accuracy; remote sensing; majority vote; spectral-spatial classification; classification; Clustering; imagery; segmentation; hyperspectral images; Pixel
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2009.2016214

A new spectral-spatial classification scheme for hyperspectral images is proposed. The method combines the results of a pixel wise support vector machine classification and the segmentation map obtained by partitional clustering using majority voting. The ISODATA algorithm and Gaussian mixture resolving techniques are used for image clustering. Experimental results are presented for two hyperspectral airborne images. The developed classification scheme improves the classification accuracies and provides classification maps with more homogeneous regions, when compared to pixel wise classification. The proposed method performs particularly well for classification of images with large spatial structures and when different classes have dissimilar spectral responses and a comparable number of pixels.