RECONSTRUCTION OF SATELLITE IMAGES USING MODIFIED STATISTICAL ITERATIVE TECHNIQUE

Abstract

Modified Statistical Iterative Technique has been adapted to reconstruct satellite images. The adopted technique removes some of the assumptions used in the derivation of the Wiener filtering solution. Most obviously, the iterative approach we develop will require no assumptions about the underlying image generation process. The adapted filter was designed for reconstructing satellite images that are blurred with space-invariant blurring function corrupted with additive noise. Different degradation parameters, i.e. different width of blurring function and different signal to noise ratio were considered. The results using an adaptive technique were compared, quantitatively, using mean square error (MSE). Results shows that this method has better performance for reconstructing the degraded satellite images.