Fractional Conway Polynomials for Image Denoising with Regularized Fractional Power Parameters

Abstract

Image denoising is a significant image processing problem that is difficult to study. The use of fractional masks based on fractional calculus (integral and differential) operators has increased for image denoising. This paper proposes an image denoising algorithm that is based on the generalization of fractional Conway polynomials with regularized fractional power parameters. We operate the structures of fractional masks (differential and integral) by using $$n \times n$$n×n processing masks on eight directions. The performance of the proposed algorithm is evaluated on the basis of visual perception and peak signal-to-noise ratio (PSNR). Theoretical analysis and experimental results demonstrate that the improvements achieved according to visual perception and PSNR values are comparable with Gaussian and Wiener filters.