基于奇异值分解的运动模糊图像广义逆恢复方法

鲁晓东

鲁晓东. 基于奇异值分解的运动模糊图像广义逆恢复方法[J]. 应用光学, 2013, 34(1): 90-94.
引用本文: 鲁晓东. 基于奇异值分解的运动模糊图像广义逆恢复方法[J]. 应用光学, 2013, 34(1): 90-94.
LU Xiao-dong. Restoration of motion-blurred image by generalizedinverse method based on SVD[J]. Journal of Applied Optics, 2013, 34(1): 90-94.
Citation: LU Xiao-dong. Restoration of motion-blurred image by generalizedinverse method based on SVD[J]. Journal of Applied Optics, 2013, 34(1): 90-94.

基于奇异值分解的运动模糊图像广义逆恢复方法

详细信息
    通讯作者:

    鲁晓东(1971-),男,浙江舟山人,硕士,主要从事图像与信号处理方面的研究工作。 Email: lxd7725@163.com

  • 中图分类号: TP391.41

Restoration of motion-blurred image by generalizedinverse method based on SVD

  • 摘要: 当线性模型应用于运动模糊模糊图像的恢复时,方程的最小二乘解是恢复图像的最优线性无偏估计。由于图像退化过程的不适定性,当观测值受到噪声干扰时,该解往往会远偏离真值。为了克服这个问题,通过对退化矩阵的奇异值分解,提取其不易受干扰的子空间,用该空间重构的逆矩阵具有良好抑噪能力,使图像在较长的运动模糊尺度内恢复时保持较低的失真。
    Abstract: When a method based on linear model is applied for motion-blurred image restoration, its least square solution is the best linear unbiased estimator for the restoration. Because of the ill-conditioned degeneration of the image, this solution always diverges far from the original value in the case of noise jamming. In order to overcome the shortage, some subspaces not susceptible to noise were extracted by singular value decomposition (SVD) of degenerate matrix. A more robust inverse matrix was reconstructed on these spaces and it ensured the restored image had less distortion in a longer blurred length.
  • [1]刘微,朱  明,李向荣,等.运动模糊图像恢复过程中的几个关键问题[J].电子器件,2005,28(3) :600-603.
    LIU Wei,ZHU Ming,LI Xiang-rong,et al.Questions in restoration of motion-blurred image[J]. Chinese Journal of Electron Devices, 2005,28(3) :600-603.(in Chinese with an English abstract)
    [2]胡海根.相对运动的模糊图像复原的算法研究[J].机电工程,2003,20(5):136-138.
    HU Hai-gen. Arithmetic research of blurred image restoration about relative motion[J]. Mechanical & Electrical Engineering Magazine, 2003,20(5):136-138. (in Chinese with an English abstract)
    [3]吴魁,任  丹,吴建华.运动模糊图像的Moore-Penrose逆法恢复[J].江西科学,2002,20(4):195-197.
    WU Kui,REN Dan,WU Jian-hua. A Moore-Penrose inverse method for the restoration of motion blurred image[J]. Jiangxi Science, 2002,20(4):195-197. (in Chinese with an English abstract)
    [4]苗晴,唐斌兵,周海银.基于约束最小二乘的空域迭代图像复原[J].仪器仪表学报, 2005,26(8): 657-659.
    MIAO Qing, TANG Bin-bing, ZHOU Hai-yin. Image restoration based on constrained least square and space iterative[J]. Chinese Journal of Scientific Instrument, 2005,26(8): 657-659. (in Chinese with an English abstract)
    [5]温广瑞,张西宁,屈梁生.奇异分解技术在声音信息分离中的应用[J].西安交通大学学报,2003,37(1):36-40.
    WEN Guang-rui,ZHANG Xi-ning,QU Liang-sheng. Application of singular value decomposition and short time fourier transform in sound information separation[J]. Journal of Xi-an Jiaotong University, 2003,37(1):36-40. (in Chinese with an English abstract)
    [6]夏良正.数字图像处理[M].南京:东南大学出版社,1999.
    XIA Liang-zheng.Digital image processing[M].Nanjing:Southeast University Press, 1999.(in Chinese)
    [7]刘慧.矩阵论及应用[M].北京:化学工业出版社,2003.
    LIU Hui.Matrix theory and its applications[M]. Beijing: Chemical Industry Press, 2003.(in Chinese)
    [8]张贤达.矩阵分析与应用[M].北京:清华大学出版社,2005.
    ZHANG Xian-da. Matrix analysis and applications[M]. Beijing: Tsinghua University Press, 2005.(in Chinese)
    [9]刘 超,汪元美.超声逆散射图像重建问题中截断奇异分解正则化方法研究[J].中国图像图像学报,2003,8(10):1146-1152.
    LIU Chao, WANG Yuan-mei.The study on truncated singular value decomposition method in ultrasound inverse scattering image reconstruction[J]. Journal of Image and Graphics, 2003,8(10):1146-1152. (in Chinese with an English abstract)
    [10]赵梨丰,姚玉林. SVD方法在信号重构中的应用[J].青岛海洋大学学报,1999,29(1):101-106.
    ZHAO Li-feng, YAO Yu-ling. Signal reconstruction by the SVD method[J]. Journal of Ocean University of Qingdao,1999,29(1):101-106. (in Chinese with an English abstract)
    [11]刘丹.计算机图像处理的数学和算法基础[M].北京:国防工业出版社,2005.
    LIU Dan. Mathematics and algorithm base for computer image processing[M].Beijing:National Defence Industry Press, 2005.(in Chinese)
计量
  • 文章访问数:  2328
  • HTML全文浏览量:  94
  • PDF下载量:  464
  • 被引次数: 0
出版历程
  • 刊出日期:  2013-01-14

目录

    /

    返回文章
    返回