[1] Li Wenshu, Luo Jianhua, Liu Qiegen, et al. Iterative regularization method for image denoisingwith adaptive scale parameter [J]. Journal of Southeast University (English Edition), 2010, 26 (3): 453-456. [doi:10.3969/j.issn.1003-7985.2010.03.016]

Copy

Iterative regularization method for image denoisingwith adaptive scale parameter()

一种变尺度参数的迭代正则去噪算法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

26

Issue:

2010 3

Page:

453-456

Research Field:

Computer Science and Engineering

Publishing date:

2010-09-30

Info

Title:

Iterative regularization method for image denoisingwith adaptive scale parameter

一种变尺度参数的迭代正则去噪算法

Author(s):

Li Wenshu^{1, 2}, Luo Jianhua¹, Liu Qiegen¹, He Fangfang², Wei Xiujin²

¹School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200240, China
²College of Informatics and Electronics, Zhejiang Sci-Tech University, Hangzhou 310018, China

李文书^{1, 2}, 骆建华¹, 刘且根¹, 何芳芳², 魏秀金²

¹上海交通大学生命科学技术学院, 上海200240; ²浙江理工大学信电学院, 杭州310018

Keywords:

iterative regularization model(IRM);  total variation;  varying scale parameter;  image denoising

迭代正则化模型(IRM);  总变差;  变尺度参数;  图像去噪

PACS:

TP391.4

DOI:

10.3969/j.issn.1003-7985.2010.03.016

Abstract:

In order to decrease the sensitivity of the constant scale parameter, adaptively optimize the scale parameter in the iteration regularization model(IRM)and attain a desirable level of applicability for image denoising, a novel IRM with the adaptive scale parameter is proposed. First, the classic regularization item is modified and the equation of the adaptive scale parameter is deduced. Then, the initial value of the varying scale parameter is obtained by the trend of the number of iterations and the scale parameter sequence vectors. Finally, the novel iterative regularization method is used for image denoising. Numerical experiments show that compared with the IRM with the constant scale parameter, the proposed method with the varying scale parameter can not only reduce the number of iterations when the scale parameter becomes smaller, but also efficiently remove noise when the scale parameter becomes bigger and well preserve the details of images.

为了降低迭代正则化中定尺度参数对快速收敛的敏感性、自适应地优化尺度参数并提高其去噪效果, 提出了一种变尺度参数的迭代正则化去噪算法.首先, 修改了经典的正则化项, 并推导出尺度参数公式;然后, 通过研究迭代次数与尺度参数序列的变化趋势, 得到变尺度参数的初始值;最后, 进行正则化去噪.数值实验表明:相对于恒定尺度参数的IRM算法, 变尺度参数IRM算法比选取尺度参数偏小的IRM算法迭代次数大大减少;比选取尺度参数偏大的IRM算法去噪效果更为明显, 并较好地保持了图像的细节.

References:

[1] Rudin L, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms [J]. Physica D, 1992, 60(1/2/3/4): 259-268.
[2] Devore R, Jawerth B, Lucier B. Image compression through wavelet transform coding [J]. IEEE Trans Information Theory, 1992, 38(2): 719-746.
[3] Donoho D L. Denoising by soft-threshold [J]. IEEE Trans Information Theory, 1995, 41(3):613-627.
[4] Osher S, Solè A, Vese L. Image decomposition and restoration using total variation minimization and the H-1 norm[J]. SIAM Journal on Multiscale Modeling and Simulation, 2003, 1(3): 349-370.
[5] Burger M, Gilboa G, Osher S, et al. Nonlinear inverse scale space methods [J]. Communications in Mathematical Science, 2006, 4(1):175-208.
[6] Chambolle A, DeVore R A, Lee N Y, et al. Nonlinear wavelet image processing: variational problems, compression, and noise removal through wavelet shrinkage [J]. IEEE Trans Image Processing, 1998, 7(3): 319-335.
[7] Chambolle A, Lucier B J. Interpreting translation-invariant wavelet shrinkage as a new image smoothing scale space [J]. IEEE Trans Image Processing, 2001, 10(7): 993-1000.
[8] Steidl G, Weickert J, Brox T, et al. On the equivalence of soft wavelet shrinkage, total variation diffusion, total variation regularization, and SIDEs [J]. SIAM Journal on Numerical Analysis, 2004, 42(2): 686-713.
[9] Xu J, Osher S. Iterative regularization and nonlinear inverse scale space applied to wavelet-based denoising [J]. IEEE Trans Image Processing, 2007, 16(2): 534-544.
[10] Meyer Y. Oscillating patterns in image processing and nonlinear evolution equations [M]. Boston: American Mathematical Society, 2001:42-45.
[11] Osher S, Burger M, Goldfarb D, et al. An iterative regularization method for total variation based image restoration [J]. Multiscale Modeling and Simulation, 2005, 4(2): 460-489.
[12] Bregman L. The relaxation method of finding the common points of convex sets and its application to the solution of problems in convex programming [J]. USSR Computational Mathematics and Mathematical Physics, 1967, 7(3): 200-217.
[13] Hao B B, Li M, Feng X C. Wavelet iterative regularization for image restoration with varying scale parameter [J]. Signal Processing: Image Communication, 2008, 23(6): 433-441.
[14] Liu B, King K, Steckner M, et al. Regularized sensitivity encoding(SENSE)reconstruction using Bregman iterations [J]. Magnetic Resonance in Medicine, 2009, 61(1):145-152.
[15] Chambolle A. An algorithm for total variation minimization and applications [J]. Journal of Math, Imaging and Vision, 2004, 20(1/2): 89-97.

Memo

Memo:

Biography: Li Wenshu(1975—), male, doctor, associate professor, wshlee@163.com.
Foundation items: The National Natural Science Foundation of China(No.60702069), the Research Project of Department of Education of Zhejiang Province(No.20060601), the Natural Science Foundation of Zhejiang Province(No.Y1080851), Shanghai International Cooperation on Region of France(No.06SR07109).
Citation: Li Wenshu, Luo Jianhua, Liu Qiegen, et al. Iterative regularization method for image denoising with adaptive scale parameter [J].Journal of Southeast University(English Edition), 2010, 26(3):453-456.

Common functions