A Novel Variational Model with Strict Convexity for Multiplicative Noise Removal

In this paper, a novel variational model with strict convexity for removing multiplicative noise from images is proposed and studied. Firstly, by applying maximum likelihood estimation method and the Bayesian formulation, the variational model is derived. Then, we use an alternating minimization algorithm to find out the minimizer of the objective function, and prove the existence of the minimizer for the underlying variational problem in theory. Finally, Our experimental results show that the quality of images denoised by the proposed method is quite good, and the proposed model is superior to the existing key models in preventing the images from stair-casing, and in restoring more texture details of the denoised image.