Classification of Remote Sensing Imagery Based on Density and Fuzzy c-Means Algorithm

Abstract

The goal of data clustering is to divide a set of data into different clusters, so that the data in the same cluster show some similar characteristics. There are many clustering methods for satellite image segmentation, such as k-means, c-means, iso-data, minimum distance algorithms. Each method has certain advantages and disadvantages, but generally they are based on brightness value to divide the pixels of the image in to clusters. Actually, the probability of occurrence of frequency of appearance of pixel has certain effects on clustering results. In this article, the authors propose a method for clustering satellite imagery based on density. It consists of two main steps: find cluster centroid using density and data clustering using fuzzy c-Means algorithm (DFCM). The results obtained in this study can be used to potentially improve classification accuracy of satellite image.