Land Cover Classification using GA based Fuzzy Clustering Techniques for Remotely Sensed Data

Remote Sensing Imagery is used by the Government and private agencies for the wide range of applications from military to farm development. Fuzzy c-means clustering is an effective algorithm, but the random selection in center points makes iterative process falling into the local optimal solution easily. In this Paper, a novel clustering method is developed using GA based clustering techniques. This technique enables the clustering to be performed by taking the initial centroid using mode function which allows the iterative algorithm to meet to a ―better‖ local minimum. Then the GA based improvement algorithm to get better cluster quality. The study area taken here is the Theni region, Tamil Nadu.