IMAGE CLASSIFICATION ALGORITHM-BASED ON THE RBF NEURAL-NETWORK AND K-MEANS

This Letter presents the implementation of an algorithm using the radi al basis function (RBF) neural networks combined with the technique of K-means for the classification of optical and radar remote sensing im ages. During the convergence of RBF networks, K-means serves for the i nitialization of class centres. An automatic self-organizing classific ation algorithm is constructed based on the RBF networks and split and merge technique. Experimental results show that this algorithm is an effective classifier compared to some conventional methods.