Image Denoising using Adaptive Wiener Filters with Radial Basis Function and its comparison with Wavelet transform based methods

Abstract

Removal of noise from images is the fundamental process of computer vision and image processing. The basic purpose of image denoising is to restore the noisy images and to enhance the image for better understanding to other systems (or humans). Since many different approaches of image denoising have been proposed for a decade, amongst them removal of noise by wavelet transform produces some desired results. This paper proposes the integration of adaptive wiener filter and Radial Basis Function Neural Networks (RBFNN) for image denoising. Furthermore, a comparison between the proposed method and wavelet transform based methods has been carried out on the basis of Mean Square Error and PSNR. Separation results fetched from the tested images demonstrates the feasibility of the approach presented in this paper