Non-convex TGV regularized [formula omitted]-norm fidelity model for impulse noise removal

Abstract

Aiming at preserving the structural features of images from degradations contaminated by impulse noise, this article proposes a novel strategy that inherits the characteristics of ℓ0-norm data fidelity and non-convex total generalized variation regularizer. The ℓ0-norm fidelity is more conducive to removing impulse noise, while the non-convex total generalized variation penalty term is both good at eliminating the staircase artifacts and maintaining neat contours. In addition, a modified alternating minimization algorithm is constructed to optimize the solution of the developed model, which merges the popular iteratively reweighted ℓ1 algorithm and primal-dual approach. Meanwhile, the convergence property of the designed algorithm is briefly presented. Finally, in the experimental part, exhaustive simulation experiments are carried out to demonstrate the effectiveness of the introduced scheme for removing impulse noise. As observed in the numerical results, our scheme possesses obvious superiorities in both visual effects and quantitative comparisons, in contrast to some existing popular image restoration methods.