Context-adaptive anisotropic diffusion for image denoising

被引:18
作者
Li, H. C. [1 ]
Fan, P. Z. [1 ]
Khan, M. K. [2 ]
机构
[1] SW Jiaotong Univ, Sichuan Prov Key Lab Informat Coding & Transmiss, Chengdu 610031, Peoples R China
[2] King Saud Univ, Ctr Excellence Informat Assurance CoEIA, Riyadh 92144, Saudi Arabia
基金
中国国家自然科学基金;
关键词
EDGE-DETECTION;
D O I
10.1049/el.2011.3994
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
To mitigate smoothing of image features in anisotropic diffusion filtering, a novel scheme called context-adaptive anisotropic diffusion is proposed for image denoising via a weighted diffusivity function, which encodes the impact of contextual discontinuities and can adaptively control the smoothing speed for improving the capability of feature preservation along with noise removal. Experimental results validate the effectiveness of the proposed method.
引用
收藏
页码:827 / 828
页数:2
相关论文
共 7 条
  • [1] Robust anisotropic diffusion
    Black, MJ
    Sapiro, G
    Marimont, DH
    Heeger, D
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (03) : 421 - 432
  • [3] IMAGE SELECTIVE SMOOTHING AND EDGE-DETECTION BY NONLINEAR DIFFUSION
    CATTE, F
    LIONS, PL
    MOREL, JM
    COLL, T
    [J]. SIAM JOURNAL ON NUMERICAL ANALYSIS, 1992, 29 (01) : 182 - 193
  • [4] A REGULARIZED ITERATIVE IMAGE-RESTORATION ALGORITHM
    KATSAGGELOS, AK
    BIEMOND, J
    SCHAFER, RW
    MERSEREAU, RM
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1991, 39 (04) : 914 - 929
  • [5] SCALE-SPACE AND EDGE-DETECTION USING ANISOTROPIC DIFFUSION
    PERONA, P
    MALIK, J
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (07) : 629 - 639
  • [6] Image quality assessment: From error visibility to structural similarity
    Wang, Z
    Bovik, AC
    Sheikh, HR
    Simoncelli, EP
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (04) : 600 - 612
  • [7] Noise reduction and edge detection via kernel anisotropic diffusion
    Yu, Jinhua
    Wang, Yuanyuan
    Shen, Yuzhong
    [J]. PATTERN RECOGNITION LETTERS, 2008, 29 (10) : 1496 - 1503