Satellite Imagery Enhancement Using K-Mean Clustering

Abstract

Several conventional contrast enhancement techniques adopt a global approach to enhance all the brightness level of the image. However, it is usually difficult to enhance all land cover classes appearing in the satellite images, because local contrast information and details may be lost in the dark and bright areas. In this paper, a k-mean clustering image enhancement method is developed to partition the image pixel values into various degrees of associates in order to compensate the local brightness lost in the dark and bright areas. The algorithm contains three stages: First, the satellite image is transformed from gray-level space to membership space by K-Means clustering. Second, appropriate stretch model of each cluster is constructed based on corresponding memberships. Third, the image is transformed back to the gray-level space by merging stretched gray values of each cluster. Finally, the performance of the proposed scheme is evaluated visually and quantitatively. The results show that the proposed method can enhance the image to a quality visualization and superior index measurement.

Key words: Satellite image, K-Mean clustering, Gray- level space, Remote sensing technology, Stretch model, Enhancement algorithms.