A fractional-order adaptive regularization primal-dual algorithm for image denoising

摘要

This paper aims to develop a fractional-order model and a primal-dual algorithm for image denoising, where a regularization parameter can be adjusted adaptively according to Morozov discrepancy principle at each iteration to ensure that the denoised image retains in a specific set. In the light of saddle-point theory, the convergence of our proposed algorithm is guaranteed. Simulations with comparisons are carried out to demonstrate the effectiveness of our proposed algorithm for image denoising. (C) 2014 Elsevier Inc. All rights reserved.