摘要：Image quality parameters are the figure of merit widely used in the image processing applications to analyze and compare the output image with the input image. These measures are widely used in image compression, segmentation, feature extraction, object detection and tracking, and image based measurements. In this paper, these parameters measure the similarity or dissimilarity between the two images on the basis of comparing the corresponding pixels of the two images and present a numerical value as a result. The segmentation is one of the most challenging and important process in the image analysis. The success of the image analysis is based on the result produced in the segmentation stage. This paper presents a comparative study of the segmentation of high resolution satellite images in RGB and HSV color spaces using modified k-means clustering algorithm. The segmented images are compared with the original input images by using number of bivariate image quality parameters. To test the efficiency and robustness of the proposed method, the experiments are performed on GeoEye-1 satellite images.
