高阶混合正则化图像盲复原方法

唐述; 龚卫国

doi:10.3788/OPE.20132101.0151

您当前的位置：

首页 >

文章列表页 >

高阶混合正则化图像盲复原方法

信息科学 | 更新时间：2020-08-12

- 高阶混合正则化图像盲复原方法
- High-order hybrid regularization method for image blind restoration
- 光学精密工程 2013年21卷第1期页码：151-157
- 作者机构：
  
  重庆大学光电工程学院光电技术及系统教育部重点实验室
- 作者简介：
- 基金信息：
  
  中央高校基本科研业务费资助基金();公安部应用创新项目();重庆市自然科学基金()
- DOI：10.3788/OPE.20132101.0151
  中图分类号： TN391.4
- 收稿日期：2012-06-15，
  
  修回日期：2012-09-08，
  
  网络出版日期：2013-01-24，
  
  纸质出版日期：2013-01-15
- 稿件说明：
移动端阅览
唐述龚卫国. 高阶混合正则化图像盲复原方法[J]. 光学精密工程, 2013,21(1): 151-157

TANG Shu GONG Wei-guo. High-order hybrid regularization method for image blind restoration[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 151-157
唐述龚卫国. 高阶混合正则化图像盲复原方法[J]. 光学精密工程, 2013,21(1): 151-157 DOI： 10.3788/OPE.20132101.0151.

TANG Shu GONG Wei-guo. High-order hybrid regularization method for image blind restoration[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 151-157 DOI： 10.3788/OPE.20132101.0151.

摘要

提出了一种高阶混合正则化图像盲复原方法，用于实现模糊噪声图像的清晰化盲复原。根据自然图像边缘的稀疏特性，对图像的边缘细节成分进行了全变差(total variation TV)正则化约束，根据自然图像同性质平滑区域内像素值的变化规律，将一种高阶的类Tikhonov正则化约束运用于图像的平滑区域中，提出了一种新的高阶混合正则化模型。最后，提出一种多变量分裂布雷格曼(Multi-variable Split Bregman MSB)最优化迭代策略对提出的模型进行最优化求解。实验结果表明，提出的方法能够很好地保护图像的边缘细节，同时有效地消除图像平滑区域内的阶梯和假边缘瑕疵。与近几年的一些较好的图像盲复原方法相比，本文方法的信噪比增量(increase of the signal to noise ratio ISNR)增加了0.03~2.5 dB。

Abstract

A high-order hybrid regularization method for image blind restoration was proposed to restore blurry-noisy images blindly. Because of the sparse edges in a natural image

the Total Variation(TV) regularization restriction was applied to the edge texture component. According to the variation regulation of pixels in homogeneous smooth regions of the natural image

a high-order Tikhonov-like regularization restriction was applied to the smooth regions of the image

and a new model which combines the TV regularization restriction and the high-order Tikhonov-like regularization restriction was proposed. Finally

a multi-variable Split-Bregman (MSB) optimized iterative scheme was proposed to recover the image. A large number of experiments have been performed. The results prove that the proposed method is able to preserve the image edges while avoiding staircase effects and false edges in the smooth regions. The proposed method is compared with several recent image blind restoration methods

and results show that the Increment of Signal-to-noise Ratio(ISNR) has been improved between 0.03 dB and 2.5 dB.

关键词

Keywords

references

GONZALEZ R C，WOODS R E. 数字图像处理[M]. 阮秋琦, 阮宇智译, 2版, 北京：电子工业出版社,2003:1-220.GONZALEZ R C, WOODS R E. Digital Image Processing[M]. RUAN Q Q, RUAN Y ZH， Translation, 2nd ed, Beijing: Publishing House of Electronics Industry, 2003: 1-220. (in Chinese)[2]乔建苹，刘琚.基于支撑向量机的盲超分辨率图像复原算法[J]. 电子学报, 2007, 35(10): 1927-1933.QIAO J P, LIU J. A SVM-based blind super-resolution image restoration algorithm [J]. Acta Electronica Sinica, 2007, 35(10): 1927-1933. (in Chinese)[3]RUDIN L, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D, 1992, 60: 259-268.[4]CHAN T F, WONG C K. Total variation blind deconvolution [J]. IEEE Transactions on Image Processing, 1998, 7 (3): 370-375.[5]MONEY J H, KANG S H. Total variation minimizing blind deconvolution with shock filter reference[J]. ELSEVIER Image and Vision Computing, 2008, 26 (2): 302-314.[6]BABACAN S D, MOLINA R, KATSAGGELOS A K. Variational Bayesian blind deconvolution using a total variation prior [J]. IEEE Transactions on Image Processing, 2009, 18 (1): 12-26.[7]ALMEIDA M S C, ALMEIDA L B. Blind and semi-blind deblurring of natural images [J]. IEEE Transactions on Image Processing, 2010, 19 (1): 36-52.[8]PANG Z P, YANG Y F. A projected gradient algorithm based on the augmented Lagrangian strategy for image restoration and texture extraction[J]. ELSEVIER Image and Vision Computing, 2011, 29 (2-3): 117-126.[9]LI W H, LI Q L, GONG W G, et al.. Total variation blind deconvolution employing split Bregman iteration [J]. ELSEVIER Journal of Visual Communication and Image Representation, 2012, 23 (3): 409-417.[10]SHAN Q, JIA J Y, AGARWALA A. High-quality motion deblurring from a single image [J]. ACM Transactions on Graphics, 2008, 27 (3): Article 73:1-73:10.[11]温博，张启衡，张建林. 应用自解卷积和增量Wiener滤波实现迭代盲图像复原\[J\]. 光学精密工程, 2011, 19(12):3050-3055.WEN B, ZHANG Q H, ZHANG J L. Realization of iterative blind image restoration by self deconvolution and increment Wiener filter\[J\]. Opt. Precision Eng., 2011, 19(12): 3050-3055. (in Chinese)[12]赵金宇，吴元昊，贾建禄，乔兵，王斌，汪宗洋，马鑫雪. 基于实时波前信息的图像复原\[J\]. 光学精密工程, 2012, 20(6): 1351-1356.ZHAO J Y, WU Y H, JIA J H, QIAO B, WANG B, WANG Z Y, MA X X. Image restoration based on real time wave-front information\[J\]. Opt. Precision Eng., 2012, 20(6): 1351-1356. (in Chinese)

浏览量

119

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

非凸高阶全变差正则化自然光学图像盲复原

多范数混合约束的正则化图像盲复原