Adaptive weight-modified Riesz mean filter for high-density salt-and-pepper noise removal

Abstract This paper introduces a novel filter, the adaptive weight-modified Riesz mean filter (AWMRmF), designed for the effective removal of high-density salt-and-pepper noise. AWMRmF integrates a pixel weight function and adaptivity condition inspired by the different adaptive modified Riesz mean filter. In this study, the performance of AWMRmF was evaluated against established filters such as adaptive frequency median filter, adaptive weighted mean filter, adaptive Ces´aro mean filter, adaptive Riesz mean filter, and improved adaptive weighted mean filter. The assessment was conducted on 26 typical test images, varying noise levels from 60 to 95%. The findings indicate that, in terms of both peak signal-to-noise ratio and structural similarity metrics, AWMRmF outperformed other state-of-the-art filters. Furthermore, AWMRmF demonstrated superior performance in mean PSNR and SSIM results as well.