An image denoising approach based on adaptive nonlocal total variation

Abstract

In the nonlocal total variation (NLTV) model the constant regularization parameter λ cannot adaptively control the balance between the regularization term and the fidelity term, which may results in over-smoothing and the more losing image details in non-flat areas when λ is small, or insufficient noise removal in flat areas when λ is large. It is better that λ has different values according to the characteristics of image areas. In this paper, we introduce an adaptive regularization parameter λ(x) which can recognize flat areas and non-flat areas of an image and propose an improved NLTV model by replacing regularization parameter λ in NLTV model with the function λ(x). In addition, we calculate the similarity weight function of our model from the pre-filtered image to reduce the influence of noise on it. Experimental results demonstrate our approach outperforms some existing methods in terms of objective criteria and subjective visual perception.