A new modified fuzzy c-means algorithm for multispectral satellite images segmentation

The purpose of cluster analysis is to partition a data set into a number of disjoint groups or clusters. The members within a cluster are more similar to each other than members from different clusters. The fuzzy c-means (FCM) clustering is an iterative partitioning method that produces optimal c-partitions. Since the standard FCM algorithm takes a long time to partition a large data set. Because FCM program must read the entire data set into a memory for processing. This paper presents a method to speed up the FCM algorithm by reducing the number of numeric operations performed in each iteration, while keeping the exact result as the standard algorithm. The application of this method to multispectral satellite images has been evaluated, about 40% of time saving was obtained.