Adaptive parameter estimation for total variation image denoising

Abstract

In this paper, we propose an adaptive parameter estimation algorithm for total variation image denoising. The de-noising framework consists of two-stage regularization parameter estimation. Firstly, we consider the fidelity of denoised image, and model a convex optimization function of denoised result. Under the results of fast gradient projection (FGP) method with a series of regularization parameters, the convex function converges to an optimal solution, which corresponds to the firststage optimal value of regularization parameter. Second, considering parameter estimation error and noise sensitivity, we build an iterative link between the dual approach function and regularization parameter. At the end of iteration, the regularization parameter reaches a stable value while the corresponding denoised result has a better visual quality. Comparing with several state-of-the-art algorithms, a large number of numerical experiments confirm that the proposed parameter estimation is highly effective, and the final denoised image has a good performance in PSNR and SSIM, especially in low SNR environment.