Blind image restoration based on normalized hyper laplacian prior term

WANG Guo-Dong; XU Jie; PAN Chen-kuan; LIU Cun-liang; YANG Jin-bao

doi:10.3788/OPE.20132105.1340

您当前的位置：

首页 >

文章列表页 >

Blind image restoration based on normalized hyper laplacian prior term

更新时间：2020-08-12

- Blind image restoration based on normalized hyper laplacian prior term
- Optics and Precision Engineering Vol. 21, Issue 5, Pages: 1340-1348(2013)
- 作者机构：
  
  青岛大学信息工程学院2. 青岛大学物理科学学院
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132105.1340
  CLC： TP394.1
- Received：26 November 2012，
  
  Revised：14 January 2013，
  
  Published Online：24 May 2013，
  
  Published：15 May 2013
- 稿件说明：
移动端阅览
王国栋徐洁潘辰宽刘存良杨金宝. 基于归一化超拉普拉斯先验项的运动模糊图像盲复原[J]. 光学精密工程, 2013,21(5): 1340-1348

WANG Guo-Dong XU Jie PAN Chen-kuan LIU Cun-liang YANG Jin-bao. Blind image restoration based on normalized hyper laplacian prior term[J]. Editorial Office of Optics and Precision Engineering, 2013,21(5): 1340-1348
王国栋徐洁潘辰宽刘存良杨金宝. 基于归一化超拉普拉斯先验项的运动模糊图像盲复原[J]. 光学精密工程, 2013,21(5): 1340-1348 DOI： 10.3788/OPE.20132105.1340.

WANG Guo-Dong XU Jie PAN Chen-kuan LIU Cun-liang YANG Jin-bao. Blind image restoration based on normalized hyper laplacian prior term[J]. Editorial Office of Optics and Precision Engineering, 2013,21(5): 1340-1348 DOI： 10.3788/OPE.20132105.1340.

摘要

基于变分方法提出了一种运动模糊退化图像的盲复原算法。考虑自然场景的图像梯度符合长拖尾概率分布，提出的方法采用归一化的超拉普拉斯先验项作为变分能量方程中的光滑项，从而有利于图像在去模糊的求解过程中正确解收敛。由于建立的能量方程不是严格凸的函数，故引入了分裂方法进行求解。整个运动模糊退化图像的盲复原过程在多尺度框架下由粗到细尺度渐进执行。最后利用估计出的点扩展函数计算清晰图像。相对于传统的盲复原算法，本文提出的算法不需要预测图像的梯度信息和对梯度进行筛选，直接求解能量方程就能够得到相应的正确解。得到的结果验证了本文算法的有效性。

Abstract

An blind image restoration method for degraded motion images is proposed based on the variational method. As image gradient is coincident with the probability distribution of heavy-tailed characteristics in a natural scene

the method uses normalized hyper Laplacian prior term as a smooth term of variational energy equation to converge the solution of the equation exactly in image debluring. To reduce the complexity of equation solution

a fast method called split method is introduced. A multi-scale framework is established to perform the deblur procedure from large scale to small scale until the blur kernel is gotten. Finally

the estimated kernel function and clear image are used as the initial value for the next scale. Using the estimated kernel

the final clear image can be gotten by the total variation method. As compared with traditional image restoration methods

the proposed method can obtain the exact solution by direction solution of the energy equation conveniently without predetermining and selecting the image gradients. Experiments demonstrate the feasibility and validity of the proposed method.

关键词

Keywords

references

CHAN T, WONG C. Total variation blind deconvolution [J]. IEEE Tran. Image Processing, 1998, 7(3):370-375.[2]FERGUS R, SINGH B, HERTZMANN A, et al.. Removing camera shake from a single photograph [J]. ACM Transaction on Graphics, 2006, 25(3):787-794.[3]SHAN Q, JIA J, AGARWALA A .High-quality motion deblurring from a single image [J]. ACM Transaction on Graphics, 2008, 27(3):731-740.[4]LEVIN A, WEISS Y, DURAND E, et al.. Understanding and evaluating blind deconvolution algorithms \[C\]. CVPR, 2009:1964-1971.[5]HUI J, LIU C. Motion blur identification from image gradients \[C\]. CVPR, 2008:1-8.[6]CHO S, LEE S. Fast motion deblurring \[C\]. Proc. of SIGGRAPH ASIA, 2009:1-8.[7]XU L and JIA J. Two-Phase Kernel Estimation for Robust Motion Deblurring \[C\]. ECCV, 2010: 157-170.[8]HONG H, PARK K. Single-image motion deblurring using adaptive anisotropic regularization [J]. Optical Engineering, 2010, 49(9): 097008-1-13.[9]RASKAR R, AGRAWAL A, TUMBLIN J. Coded exposure photography: Motion deblurring via fluttered shutter [J]. ACM Transaction on Graphics, 2006, 25(3):795-804.[10]陈前荣, 陆启生, 成礼智. 基于方向微分的运动模糊方向鉴别 [J]. 中国图象图形学报, 2005, 10(5): 590-595.CHEN Q R, LU Q SH, CHENG L ZH. Identification of motion blur direction from motion blurred image by direction derivation method [J]. Journal of Image and Graphics, 2005, 10(5): 590-595. (in Chinese)[11]胡春华, 马旭东, 戴先中. 基于TVGA正则化的室内运动模糊图像恢复 [J]. 中国图象图形学报, 2007, 12(9): 1531-1536.HU CH H, MA X D, DAI X Z. Regularized motion blurred image restoration based on topkis veinott gradient approach in indoors [J]. Journal of Image and Graphics, 2007, 12(9): 1531-1536. (in Chinese)[12]赵琳, 金伟其, 陈翼男, 等. 一种新的运动模糊图像超分辨力盲复原算法 [J]. 光子学报, 2008, 37(11): 2355-2359.ZHAO L, JIN W Q, CHEN Y N, et al.. A new blind restoration of motion blurred images based on super-resolution method [J]. Acta Photonica Sinica, 2008, 37(11): 2355-2359. (in Chinese)[13]付中梁, 冯华君, 徐之海, 等. 二维任意运动形式模糊图像的恢复 [J]. 光学学报, 2010, 30(2): 369-372.FU ZH L, FENG H J, XU Z H, et al.. Restoration of image blurred by any form motion in two dimension [J]. Acta Optica Sinica, 2010, 30(2): 369-372. (in Chinese)[14]赵志刚, 程姝, 王国栋,等. 基于运动估计的模糊图像盲复原 [J]. 光电子激光, 2012, 23(10): 2010-2016.ZhAO ZH G, CHENG SH, WANG G D, et al.. Blind restoration of blurred image using motion estimation [J]. Journal of OptoelectronicsLaser, 2012, 23(10): 2010-2016. (in Chinese)[15]HURLEY N， RICKARD S. Comparing measures of sparsity [J]. IEEE Trans. Inf. Theory, 2009: 4723-4741.[16]KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure \[C\]. CVPR, 2011: 233-240. [17]OSHER S, MAO Y, DONG B, et al.. Fast linearized bregman iteration for compressive sensing and sparse denoising [J]. Commun. Math. Sci., 2010, 8(1): 93-111.[18]KRISHNAN D, FERGUS R. Fast image deconvolution using hyper-laplacian priors \[C\]. In NIPS, 2009:1033-1041.[19]LEVIN A, FERGUS R, DURAND F, et al.. Image and depth from a conventional camera with a coded aperture [J]. ACM Transaction on Graphics, 2007, 26(3): 701-709.[20]RUDIN L, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms [J]. Physica D, 1992, 60: 259-268.[21]孙辉. 相位相关技术实现离焦模糊图像运动估计 [J]. 液晶与显示，2012 , 27 (2): 223-228.SUN H. Estimation of displacement for out-of-focus blurred image using phase-only correlation [J]. Chinese Journal of Liquid Crystals and Displays, 2012 ,27 (2): 223-228. (in Chinese)

Views

129

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Blind restoration of camera shake blurred image based on L0 sparse priors

Blind moving image restoration based on sparse representation and Weber's law

Adaptive blind image restoration based on NAS-RIF algorithm

Related Author

Xiang QIU

Ming DAI

LIU Cheng-yun

CHANG Fa-liang

HUANG De-tian

WU Zhi-yong

Related Institution

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences

University of Chinese Academy of Sciences

College of Control Science and Engineering, Shandong University

Graduate University of Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰