This paper presents an improvised Moving kernel based fuzzy C-means(MKFCM) for clustering of trees, shade, building and road. It starts with the single step preprocessing procedure in which first the input image is passed through a median filter to reduce the noise and get a better image fit for segmentation. The pre-processed image is segmented using the Moving KFCM algorithm and classified using feed forward neural network classifier. KFCM with moving property is used to improve the object segmentation in satellite images. Simulation result show that classification accuracy for different regions using Moving KFCM is better than KFCM using Neural Network Classifier.
Segmentation, classification, feature extraction, Moving KFCM
