Image Denoising in Frequency Domain Based on Analogical Basis Deconstruction

Abstract

In acquisition and transmission procedures, images are often contaminated by noise in spatial and frequency domain. Image denoising is usually the first step in information extraction. At present there are many frequency domain denoising methods like low pass and high pass filtering but have not yet attained a desirable level. In this paper, we proposed a new denoising method based on Analogical Basis Deconstruction (ABD) theory. It uses only uncontaminated or slightly contaminated frequency data to recover the image through Asymptotic Iterative Estimate (AIE) algorithm. The performance of new method was tested on a simulation image and compared with the traditional frequency domain methods.