Today government and private agencies use remote sensing imagery for a wide range of applications from military applications to farm development. Remote sensing image classification is one amongst the most significant application for remote sensing. In this Paper, a novel classification method is developed using GA based clustering techniques. This method enables the clustering to be performed by taking the initial centroid using mode function which allows the iterative algorithm to converge to a “better” local minimum. Then the GA based refinement algorithm to improve the cluster quality. The study area taken here is the Theni region, Tamil Nadu