A novel weighted total variation model for image denoising

作     者：Li, Meng-Meng Li, Bing-Zhao 

作者机构：Beijing Inst Technol Sch Math & Stat Beijing Peoples R China Beijing Inst Technol Beijing Key Lab MCAACI Beijing Peoples R China 

出 版 物：《IET IMAGE PROCESSING》 (IET影像处理)

年 卷 期：2021年第15卷第12期

页      面：2749-2760页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Key R&D Program of China [2020YFC2006200] National Natural Science Foundation of China 

主　　题：image structures regularisation term weight function w image denoising TVp models Computer vision and image processing techniques HOTV model WTV model data fidelity ℓ1 norm image texture Optical, image and video signal processing novel weighted total variation model alternating direction method of multipliers image processing field ATV model TV model 

摘      要：Image denoising is a very important problem in image processing field. In order to improve denoising effects and meanwhile keep image structures, a novel weighted total variation (WTV) model is proposed in this paper. The WTV model consists of data fidelity and l1 norm based regularisation terms. In the WTV model, a weight function w in exponential form is incorporated into the regularisation term, which only depends on the given image itself without extra parameters. The nonlinearly monotone formulation of w helps to increase gaps between lower and higher frequencies of images, which is effective to highlight edges and keep textures. For solving the proposed model, the alternating direction method of multipliers is explored and the according convergence is analysed. Compared experiments of TV, HOTV, ATV and TVp models are conducted and the results show the effectiveness and efficiency of the proposed model.