Assessment of satellite image segmentation in RGB and HSV color space using image quality measures

This paper presents a comparative study of the segmentation of satellite images in RGB and HSV color space using modified fuzzy c means clustering algorithm. The segmented images are compared with the original input images by using number of bivariate image quality parameters. These parameters measure the similarity between the input and the segmented image on the basis of comparing the corresponding pixels of the two images and present a numerical value as a result. The experiments are performed on GeoEye-1 satellite images to test the efficiency and robustness of the proposed method.