Satellite Image Classification Using a Divergence-Based Fuzzy c-Means Algorithm

Abstract

A satellite image classifier scheme by using a Fuzzy c-Means (FcM) algorithm is proposed in this paper. The FcM algorithm adopted in this paper is a Gradient-based FcM with Divergence measure (GFcM(D)) and it utilizes the Divergence measure to exploit the statistical nature of the image data and thereby improves the classification accuracy. Experiments and results on a set of satellite images demonstrate that the proposed GFcM(D)-based classifier outperforms conventional algorithms such as the traditional Self-Organizing Map (SOM) and Fuzzy c-Means (FcM) in terms of classification accuracy.