English

应用科学学报 >

2014 , Vol. 32 >Issue 5: 481 - 485

DOI: https://doi.org/10.3969/j.issn.0255-8297.2014.05.008

RESEARCHNOTES

基于NSCT 和全变差模型的医学图像去噪

展开
  • 1. 上海大学通信与信息工程学院，上海200444
    2. 上海大学智慧城市研究院，上海200444
MA Xiu-li, Ph.D., lecturer, research interests including image processing, pattern recognition and intelligent information processing, E-mail: xlma@shu.edu.cn

网络出版日期: 2014-09-23

基金资助

the National Science Foundation of China (No. 61103076); the Shanghai Municipal Natural Science
Foundation (No. 12ZR1410800); the Innovation Program of Shanghai Municipal Education Commission (No. 13YZ016); the
“863”National High Technology Research and Development Program of China (No. 2013AA01A603)

收起

Medical Image Denoising Using Non-subsampled Contourlet Transform and Total Variation Model

Expand
  • 1. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
    2. Institute of Smart City, Shanghai University, Shanghai 200444, China

Online published: 2014-09-23

Fold

摘要

分析了非下采样Contourlet变换(nonsubsampled Contourlet transform, NSCT)和全变差模型的特点，提出将NSCT和全变差混合模型应用于医学图像去噪. 首先，通过NSCT变换将含噪图像分解，运用Visu萎缩阈值将NSCT系数进行处理，得到初次去噪图像. 然后，采用全变差模型对初次去噪图像进一步处理得到最终去噪图
像. 实验结果表明：该方法可以很好地保留图像细节，无论在客观上的峰值信噪比还是主观上的视觉效果都优于其他去噪方法.

关键词： 非下采样Contourlet变换; 全变差; 医学图像去噪; 峰值信噪比

本文引用格式

马秀丽1,2， 周峰1,2， 周小军1,2 . 基于NSCT 和全变差模型的医学图像去噪[J]. 应用科学学报, 2014 , 32(5) : 481 -485 . DOI: 10.3969/j.issn.0255-8297.2014.05.008

Abstract

The characteristics of non-subsampled Contourlet transform (NSCT) and total variation (TV)modeling are analyzed. A mixed model of NSCT and TV is applied to medical image denoising in this paper.NSCT filter-based decomposition of noisy medical images is performed. An initial denoised image is produced using a Visu shrink threshold algorithm. The final denoised image is obtained by processing the initial denoised image with the TV model. Experimental results show that the image details are well preserved by using the proposed method. Both peak signal-to-noise ratio (PSNR) and visual quality are superior to some other denoising algorithms.

Key words：  non-subsampled Contourlet transform; total variation; medical image denoising; peak signal-tonoise ratio (PSNR)

参考文献

[1] CHANG S Grace, YU Bin, VETTERLI Martin. An adaptive wavelet thresholding for image denoising and compression [J]. IEEE Transactions on Image Processing, 2000:  1532-1546.

[2] DO M N, VETTERLI  M. The contourlet transform: an efficient directional multiresolutional image representation [J]. IEEE Transactions on Image Processing, 2005, 14(12): 2091-2106.

[3] DA Cunha A L, ZHOU J, DO M N. The nonsubsampled contourlet transform: theory, design, and applications [J]. IEEE Transactions on Image Processing, 2006, 15(10): 3089-3101.

[4] ESLAMI R, RADHA H. Translational-invariant contourlet transform and its application to image denoising [J]. IEEE Transactions on Image Processing, 2006, 15(11):  3362-3374.

[5] Po D D Y, Do M N. Directional multiscale modeling of images using the contourlet transform [J]. IEEE Transactions on Image Processing, 2006, 15(6): 1610-1620.

[6] KANITHI Anil Kumar. Study of spatial and transform domain filters for efficient noise reduction [D]. National Institute of Technology, India, 2011.

[7] STEIDL Gabriele, WEICKERT Joachim. Relations between soft wavelet shrinkage and total variation denoising[C]//LNCS 2449, 2002: 198-205.

[8] YAN Jie, LU Wusheng. Image denoising by generalized total variation regularization and least squares fidelity [J]. Multidimensional Systems and Signal Processing, 2013.

[9] OSHER S, SOLE A, VESE L. Image decomposition and restoration using total variation minimization and the H-1 Norm [J]. SIAM Journal of Multiscale Modeling and Simulation, 2003, 1(3): 350-369.

[10] WANG Y, YANG J, YIN W, ZHANG Y. A new alternating minimization algorithm for total variation image reconstruction [J]. SIAM Journal on Imaging Sciences, 2008, 1(3): 248-272.

[11] HUY, JACOB M. Higher degree total variation (HDTV) regularization for image recovery [J]. IEEE Transactions on Image Processing, 2012, 21(5): 2559-2571.
Options
文章导航

/

〈 〉