CIELAB Color Space based High Resolution Satellite Image Segmentation using Modified Fuzzy C-Means Clustering

This paper presented a novel approach for the segmentation of high resolution satellite images using the spatial information incorporated modified fuzzy c-means clustering algorithm. The images after preprocessing and geo referencing, the satellite images are available in RGB color space. In this device dependent and non uniform color space, the intensity and color information are mixed and also the effectiveness of the color information mainly depends upon the type of light sources used. So RGB color space is not preferred for the segmentation and pattern recognition. In this paper, this problem is solved by the application of perceptually uniform CIELab color space. Even though FCM algorithm is one of the efficient approaches for image segmentation, it doesn‟t give any spatial information which is important for clustering problems. In modified FCM clustering algorithm, the spatial information is incorporated as a function of the weighted sum of the membership function. Moreover, the noisy pixels can be eliminated by image enhancement process. The result and efficiency of the proposed approach is compared with other soft computing and non-soft computing methods.