Patch-based Contour Prior Image Denoising for Salt and Pepper Noise

TL;DR

This paper introduces a patch-based contour prior method for effectively removing salt and pepper noise from images while preserving details, utilizing contour structures and regression filtering.

Contribution

It proposes a novel patch-based denoising approach that leverages contour priors and regression filtering to improve salt and pepper noise removal.

Findings

Achieves competitive PSNR compared to state-of-the-art methods.

Preserves image details effectively during denoising.

Demonstrates good visual quality in noisy image restoration.

Abstract

The salt and pepper noise brings a significant challenge to image denoising technology, i.e. how to removal the noise clearly and retain the details effectively? In this paper, we propose a patch-based contour prior denoising approach for salt and pepper noise. First, noisy image is cut into patches as basic representation unit, a discrete total variation model is designed to extract contour structures; Second, a weighted Euclidean distance is designed to search the most similar patches, then, corresponding contour stencils are extracted from these similar patches; At the last, we build filter from contour stencils in the framework of regression. Numerical results illustrate that the proposed method is competitive with the state-of-the-art methods in terms of the peak signal-to-noise (PSNR) and visual effects.