Adaptive non-convex total variation regularisation for image restoration

被引：14
作者：
Fu, S. [1 ,2 ]
Zhang, C. [1 ]
机构：
[1] Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China
[2] Shandong Univ, Sch Math, Jinan 250100, Peoples R China
来源：
ELECTRONICS LETTERS | 2010年 / 46卷 / 13期
基金：
中国博士后科学基金; 中国国家自然科学基金;
关键词：
D O I：
10.1049/el.2010.0027
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
An adaptive non-convex total variation regularisation is proposed for blind image restoration. A flux corrected transport (FCT) technique is used to obtain a stable numerical scheme, where a spatially varying constraint allows a better restoration of image edges and fine detail. Finally, its advantages are shown in deblurring edges, denoising and restoring fine details of image simultaneously in experiments.
引用
收藏
页码：907 / U56
页数：2
相关论文
共 6 条
  • [1] [Anonymous], 2002, Applied Mathematical Sciences
  • [2] [Anonymous], IMAGE PROCESSING ANA
  • [3] [Anonymous], 1977, SOLUTIONS ILL POSED
  • [4] A feature-dependent fuzzy bidirectional flow for adaptive image sharpening
    Fu, Shujun
    Ruan, Qiuqi
    Wang, Wenqia
    Gao, Fuzheng
    Cheng, Heng-Da
    [J]. NEUROCOMPUTING, 2007, 70 (4-6) : 883 - 895
  • [5] Nonlinear Scale Space with Spatially Varying Stopping Time
    Gilboa, Guy
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (12) : 2175 - 2187
  • [6] NONLINEAR TOTAL VARIATION BASED NOISE REMOVAL ALGORITHMS
    RUDIN, LI
    OSHER, S
    FATEMI, E
    [J]. PHYSICA D, 1992, 60 (1-4): : 259 - 268
1