Motion based unsharp masking [MUSM] for extracting building from urban images

Classification of remote sensing images from urban area as a means to achieve necessitated information for some applications such as automatic map updating and GIS, planning and emergency response has become one of the challenging subjects for image processing researches. In this paper, a method for classification of remote sensing image from urban area is addressed. First, motion based unsharp masking [MUSM] is applied to the input image to enhance its high frequency components. Then, laplacian of image as input feature for the Bayesian classifier is utilized. After that, size filter is used for large and small building discrimination. The classification of small and large building using unsharp mask and Bayesian discrimination function has increased in aspect of accuracy in comparison with original Bayesian method for classification of urban area. Experiments justify the efficiency of the proposed approach.