A novel weighted anisotropic total variational model for image applications

Abstract

In this paper, a novel weighted anisotropic total variational (WATV) model is proposed for image restoration. In this model, a weight function is defined to process degraded images, which is introduced into the $$\\ell _{1}$$\n norm-based regularization. In order to efficiently compute the restored images, the alternating direction method of multipliers (ADMM) is explored and the according convergence is analyzed briefly. The proposed model is applied to recover images with blurring and noise. Compared experiments of deblurring, denoising as well as restoration are conducted to show the effectiveness and efficiency of the proposed WATV model.