Differential Evolution based Fuzzy Clustering Technique: Application to Satellite Image Segmentation

An important approach to unsupervised pixel classification in remote sensing satellite imagery is to use clustering in the spectral domain. The problem of classifying an image into different homogeneous regions is viewed as the task of clustering the pixels in the intensity space. In particular, satellite images contain landcover types some of which cover significantly large areas, while some (e.g., bridges and roads) occupy relatively much smaller regions. Detecting regions or clusters of such widely varying sizes presents a challenging task. A Differential evolution based fuzzy clustering technique, is proposed in this article. Real coded encoding of the cluster centers is used for this purpose. Results demonstrating the effectiveness of the proposed technique are provided for several synthetic data set and also statistical significance tests have been performed to establish the superiority of the proposed algorithm. Different landcover regions in remote sensing imagery have also been classified using the proposed technique to establish its efficiency.