A New Image Denoising Method Combining the Nonsubsampled Contourlet Transform and Adaptive Total Variation
一种新的结合非下采样Contourlet与自适应全变差的图像去噪方法

This paper presents a new image denoising scheme by combining the NonSubsampled Contourlet Transform (NSCT) and adaptive total variation model. The original image is first decomposed using NSCT and the image model is built based on Gaussian Scale Mixtures (GSM) model. Then the image noises are removed using Bayesian estimation, producing the preliminary denoised image after reconstruction. Then the preliminary primary denoised image is further filtered using the adaptive total variation model, producing the final denoised image. Experiments show that the proposed scheme can remove Gibbs-like artifacts and image noise effectively. Besides, it outperforms the existing schemes in regard of both the Peak-Signal-to-Noise-Ratio (PSNR) and the edge preservation ability.