The proposed technique is used to classify the satellite image into barren land, vegetation area, building area and road area. Initially, the satellite image is pre-processed and then is then segmented to have segments of barren land, vegetation area, building area and road area. The features of the segmented area are extracted and then final classification is carried out using fuzzy rule classifier. In the result section, classified output satellite images obtained are shown and proposed technique is evaluated by means of accuracy parameter. The accuracy obtained is high having an average of 92.56%. The authors also compare to normal graph cut and from the results, it is proved that their proposed technique using modified graph cut have obtained better results.