Image Noise Removal Method Based on Thresholding and Regularization Techniques

Abstract

In this article, a salt and pepper noise (SPN) removal method is proposed based on thresholding and regularization techniques. The proposed method utilizes the ability to remove noise from an image denoising model based on Total Variation (TV) regularization and characteristics of SPN. First, a technique based on the characteristic of SPN is proposed to detect noisy pixels. Second, a modified TV regularization-based method is applied to restore the above noisy pixels. In addition, numerical implementation of the model based on the Nesterov optimal method is also provided. Five test cases with various noise levels for a large natural image dataset were studied in the experiments. The peak signal-to-noise ratio and structural similarity metrics were employed to assess the image quality after denoising. The experimental results indicated that the proposed method removes SPN remarkably and outperforms state-of-the-art image denoising methods for SPN.