Image Restoration using combined Adaptive Weiner Filter and Radial Basis Function ANN with Sub-block Decomposition for Medical Applications

Image restoration is a crit ical application in image processing where Artificial Neural Network (ANN) approaches have continuously provided improved results. Here, we propose an adaptive image restoration technique based on combination of Adaptive Weiner Filter (AWF) and Radial Basis Function (RBF) which is a type of ANN with a sub-block decomposition technique. The combination of the AWF and RBF with the sub -block based decomposition provides improved results for medical images. The work init ially performs an adaptive image restoration using AWF. In this process a sequence of sub-blocks are extracted from the image and block-wise restoration performed using AWF and then RBF approach . The results when compared to tradit ional approach as well as RBF ANN sub-block decomposition approach show that the proposed Combined AWF and RBF with sub-block decomposition based approach provides better outcomes. Experimental results show that higher peak signal to noise ratio (PSNR) values are obtained using the sub-block decomposition technique which, however, contributes towards increased computational complexity.