A fuzzy hyperspectral classifier for automatic target recognition (ATR) systems

In this paper we present a fuzzy system based hyperspectral classifier for automatic target identification. The system is based on partitioning the sp ectral band space into clusters using a modified fuzzy C-Means clustering a lgorithm. Classification of each pixel is then carried out by calculating i ts fuzzy membership in each cluster. The results showed that the fuzzy hype rspectral classifier is successful in target identification using materials spectrum. Also it provides a fuzzy identification value that can be used l ater on in the decision-making stage of automatic target recognition (ATR) systems, (C) 1999 Elsevier Science B.V. All rights reserved.