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

Xiang QIU; Ming DAI

doi:10.3788/OPE.20172509.2490

您当前的位置：

首页 >

文章列表页 >

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

Information Sciences | 更新时间：2020-08-13

- Blind restoration of camera shake blurred image based on L0 sparse priors
- Optics and Precision Engineering Vol. 25, Issue 9, Pages: 2490-2498(2017)
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国科学院大学, 北京 100059
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172509.2490
  CLC： TP751.1;TP391.41
- Received：04 January 2017，
  
  Accepted：10 April 2017，
  
  Published：25 September 2017
- 稿件说明：
移动端阅览
Xiang QIU, Ming DAI. Blind restoration of camera shake blurred image based on L0 sparse priors[J]. Optics and precision engineering, 2017, 25(9): 2490-2498.
DOI：

Xiang QIU, Ming DAI. Blind restoration of camera shake blurred image based on L0 sparse priors[J]. Optics and precision engineering, 2017, 25(9): 2490-2498. DOI： 10.3788/OPE.20172509.2490.

摘要

提出了一种基于L0稀疏先验的改进正则化模糊图像盲复原算法来解决相机抖动所产生的模糊问题。根据模糊图像的梯度分布要比清晰图像稠密并且暗通道的稀疏性也相对较小这一固有属性建立了新的优化模型。针对L0范数的高度非凸性和暗通道稀疏优化过程中涉及到的非线性最小化问题，提出了一种近似线性映射矩阵，并用半二次分解法对L0最小化问题进行求解。最后，采用快速傅里叶变换在频域中对模糊核及清晰图像进行交替迭代运算得到复原图像。对多幅不同类型的模糊图像进行了实验，结果显示：复原图像平均灰度梯度高达11.411，图像信息熵达到7.304，处理365×285的图像只需8.07 s。提出的算法有效抑制了图像边缘处的振铃效应，完整保留了清晰的细节信息的同时显著提高了运算速度，并适用于多种不同类型图像的盲复原。

Abstract

An improved regularization blind restoration method based on L0 sparse prior was proposed to overcome the image blue from camera shake. A new optimization mode on the basis of inherent property which the gradient distribution of the blurred image is denser than that of the clear image and the sparse of the dark channel is relatively smaller. Aiming at the highly non-convex of L0 norm and nonlinear minimization problem in the dark channel sparse optimization process

an approximate linear map matrix based on look-up tables was proposed

and the linearized L0 minimization problem was solved by half-quadratic splitting methods. Finally

the fast Fourier transform was used to do iterative operation alternately for the fuzzy kernel and the clear image in frequency domain to obtain the restored image. Through experiments on several different types of blurred images

the results show that average gray level gradient is up to 11.411

the image entropy is up to 7.304

and it only takes 8.07s to process 365×285 images. The improved regularization algorithm effectively suppresses the ringing effect near the edge of the image

retains the integrity of clear details

improves the speed of operation significantly. The algorithm is suitable for all kinds of image restoration.

关键词

Keywords

references

阮光诗, 孙俊喜, 孙阳, 等.处理异常值的相机抖动模糊图像复原[J].中国图像图形学报, 2014, 19(5):677-682.

RUAN G SH, SUN J X, SUN Y, et al. Disposing of outliers in camera-shake blurred images restoration [J]. Journal of Image and Graphics, 2014, 19(5):677-682. (in Chinese)

孙韶杰, 吴琼, 李国辉.基于变分贝叶斯估计的相机抖动模糊图像的盲复原算法[J].电子与信息学报, 2010, 32(11):2674-2679.

SUN SH J, WU Q, LI G H. Blind image deconvolution algorithm for camera-shake deblurring based on variational bayesian estimation [J]. Journal of Electronics & Information Technology, 2010, 32(11):2674-2679. (in Chinese)

周同同. 基于相机抖动的模糊图像的盲复原实现[D]. 南京: 南京理工大学, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10288-1013165922.htm

ZHOU T T. Blind restoration of blurred image based on camera shake [D]. Nanjing:Nanjing University of Science and Technology, 2013. (in Chinese)

WANG N C, DING J J, CHEN L A, et al. Efficient image deblurring via blockwise non-blind deconvolution algorithm[C]. 2015 10th International Conference on Information, Communications and Signal Processing, IEEE, 2015:1-5.

廖永忠, 蔡自兴, 何湘华.应用半二次罚函数的图像盲去模糊[J].光学精密工程, 2015, 23(7):2086-2092.

LIAO Y ZH, CAI Z X, HE X H. Image blind deblurring with half-quadratic penalty method [J]. Opt. Precision Eng., 2015, 23(7):2086-2092. (in Chinese)

LEVIN A, WEISS Y, DURAND F, et al. Understanding and evaluating blind deconvolution algorithms [C]. IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2009:1964-1971.

廖永忠, 蔡自兴, 何湘华.快速运动模糊图像盲解卷积算法[J].光学精密工程, 2013, 21(10):2688-2694.

LIAO Y ZH, CAI Z X, HE X H. Fast algorithm for motion blurred image blind deconvolution [J]. Opt. Precision Eng., 2013, 21(10):2688-2694. (in Chinese)

DAI W H, ZHANG L, LIANG S Y. Multi-objective optimization approach to ill-posed inverse problem [C]. 4th International Conference on Natural Computation, IEEE, 2008:515-519.

余义斌, 彭念, 甘俊英.凹凸范数比值正则化的快速图像盲去模糊[J].电子学报, 2016, 44(5):1168-1173.

YU Y B, PENG N, GAN J Y. Fast blind image deblurring using ratio of concave norm to convex norm regularization [J]. Acta Electronica Sinica, 2016, 44(5):1168-1173. (in Chinese)

KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure [C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2011:233-240.

FERGUS R, SINGH B, HERTZMANN A, et al. Removing camera shake from a single photograph [C]. ACM Transactions on Graphics, 2006, 25(3):787-794.

JOSHI N, SZELISKI R, KRIEGMAN D J. PSF estimation using sharp edge prediction [C]. 2008 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2008:1-8.

SUN L B, CHO S, WANG J, et al. Edge-based blur kernel estimation using patch priors [C]. 2013 IEEE International Conference on Computational Photography, IEEE, 2013:1-8.

LEVIN A, WEISS Y, DURAND F, et al. Efficient marginal likelihood optimization in blind deconvolution [C]. 2011 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2011:2657-2664.

XU L, ZHENG S C, JIA J Y. Unnatural L 0 sparse representation for natural image deblurring [C]. 2013 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2013:1107-1114.

陶宗勤, 方贤勇, 谈业静, 等.基于双L0稀疏先验的图像运动去模糊[J].计算机应用与软件, 2016, 33(6):207-211.

TAO Z Q, FANG X Y, TAN Y J, et al. Image motion deblurring based on double L0 sparse priori [J]. Computer Applications and Software, 2016, 33(6):207-211. (in Chinese)

XU L, LU C W, XU Y, et al. Image smoothing via L 0 gradient minimization [J]. ACM Transactions on Graphics, 2011, 30(6):174.

HU Z, CHO S, WANG J, et al. Deblurring low-light images with light streaks [C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2014:3382-3389.

郭晓磊, 曹萌萌, 薄一航.基于相机运动子空间的人脸图像非均匀去模糊[J].计算机应用与软件, 2016, 33(3):197-199, 225.

GUO X L, CAO M M, BO Y H. Face image non-uniform deblurring based on camera motion subspace [J]. Computer Applications and Software, 2016, 33(3):197-199, 225. (in Chinese)

CHO H, WANG J, LEE S. Text image deblurring using text-specific properties [C]. Proceedings of the 12th European Conference on Computer Vision, Springer, 2012:524-537.

HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior [C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2009:1956-1963.

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

Views

388

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast dehazing for large format oblique images based on improved dark channel prior

Low-light image enhancement algorithm based on light scattering attenuation model

Color-line and dark channel based dehazing for remote sensing images

Blur identification algorithm to suppress parasitic ripples on infrared images

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

Related Author

ZHAO Xinghao

HE Xin

DONG Yang

OUYANG Huan

HUANG Huang

DIAN Songyi

ZHENG Xiujuan

ZHONG Yuzhong

Related Institution

Troop

Information Engineering University

College of Electrical Engineering， Sichuan University

State Key Laboratory of Modern Optical Instrumentation, Zhejiang University

Economics and Management Academy, Shangluo College

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