基于模糊结构图的模糊核估计

doi:10.3969/j.issn.0372-2112.2017.05.028

电子学报 ›› 2017, Vol. 45 ›› Issue (5): 1226-1233.DOI: 10.3969/j.issn.0372-2112.2017.05.028

基于模糊结构图的模糊核估计

方帅^1,3, 刘远东¹, 曹洋², 刘永进³

1. 合肥工业大学计算机与信息学院, 安徽合肥 230009;
2. 中国科学技术大学自动化系, 安徽合肥 230026;
3. 光电控制技术重点实验室, 河南洛阳 471009

收稿日期:2016-02-25 修回日期:2016-05-05 出版日期:2017-05-25
- 作者简介:
- 方帅女,1978年1月出生于安徽寿县.博士,教授,合肥工业大学硕士生导师,主要研究方向为计算机视觉、图像复原等.E-mail:fangshuai@hfut.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61175051，No.61175033）; 安徽省自然科学基金 (No.1508085SMF222）; 光电控制技术重点实验室和航空科学基金联合资助项目 (No.201451P4007）

Blur Kernel Estimation Using Blurry Structure

FANG Shuai^1,3, LIU Yuan-dong¹, CAO Yang², LIU Yong-jin³

1. School of Computer and Information, Hefei University of Technology, Hefei, Anhui 230009, China;
2. Department of Automation, University of Science and Technology of China. Hefei, Anhui 230026, China;
3. Key Laboratory of Optoelectronic Control Technology, Luoyang, Henan 471009, China

Received:2016-02-25 Revised:2016-05-05 Online:2017-05-25 Published:2017-05-25
- Supported by:
- National Natural Science Foundation of China (No.61175051, No.61175033); Natural Science Foundation of Anhui Province (No.1508085SMF222); Project supported by the Key Laboratory of Optoelectronic Control Technology and Aviation Science Foundation (No.201451P4007)

摘要/Abstract

摘要：

图像结构边缘对模糊核估计有重要意义.近年来许多成功的算法都致力从潜在清晰图像中分离出结构边缘形成中间图像，然后用其与模糊图像一起估计模糊核.但是这些算法忽视了从模糊图像中分离出结构边缘对应的部分，导致核估计过程中目标函数的数据项不平衡.针对这一问题，本文利用中间图像和潜在模糊核产生二值模板对模糊图像进行处理，分离出结构边缘对应的部分，并用其修正目标函数.此外本文提出采用L0范数同时约束幅值域和梯度域的正则项，从而缩小核估计的解空间.多个标准测试数据库上实验结果表面，本文算法无论在鲁棒性还是准确性方面均具有更好的效果.

关键词: 去模糊, 反卷积, 模糊核, 图像复原

Abstract:

It has been proven that structure of image play an important role in kernel estimation.In recent years,many successful algorithms propose to generate intermediate image by extracting structure from latent image,and then use it for blur kernel estimation.However,these methods ignore to extract the correspondence from input blurry image.This will cause unbalanced data item of objective function.In this paper we first exploit a mask determined by convolution of intermediate image with kernel to generate the correspondence,and then take it into data item instead of blurry image to overcome the problem.Moreover,we have found that kernel shows the properties of sparse both in intensity domain and derivatives domain.Accordingly,we apply L0-norm regularization to constrain both intensity domain and derivatives domain of kernel.Compared with the state-of-the-art algorithms,experiments across datasets showed that our algorithm achieved better performance.

Key words: deblurring, deconvolution, blur kernel, image recovery

中图分类号:

TN911.23

方帅, 刘远东, 曹洋, 等. 基于模糊结构图的模糊核估计[J]. 电子学报, 2017, 45(5): 1226-1233.

FANG Shuai, LIU Yuan-dong, CAO Yang, et al. Blur Kernel Estimation Using Blurry Structure[J]. Acta Electronica Sinica, 2017, 45(5): 1226-1233.

参考文献

[1] A Levin,Y Weiss,F Durand,W T Freeman.Understanding and evaluating blind deconvolution algorithms[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Miami:IEEE Computer Society Press,2009.1964-1971.
[2] Q Shan,J Jia,A Agarwala.High-quality motion deblurring from a single image[J].ACM Transactions,2008,Graphics-27(3):73-80.
[3] D Krishnan,T Tay,R Fergus.Blind deconvolution using a normalized sparsity measure[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Providence:IEEE Computer Society Press,2011.233-240.
[4] L Xu,S Zheng,J Jia.Unnatural L0 sparse representation for natural image deblurring[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Computer Society Press,2013.1107-1114.
[5] N Joshi,R Szeliski,D J Kriegman.PSF estimation using sharp edge prediction[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Anchorage:IEEE Computer Society Press,2008.1-8.
[6] S Cho,S Lee.Fast motion deblurring[J].ACM Transactions,2009,Graphics-28(5):1-8.
[7] L Xu,J Jia.Two-phase kernel estimation for robust motion deblurring[A].Proceedings of the European Conference on Computer Vision[C].Crete:Springer,2010.157-170.
[8] L Sun,S Cho,J Wang,J Hays.Edge-based blur kernel estimation using patch priors[A].Proceedings of the IEEE International Conference on Computational Photography[C].Cambridge:IEEE Computer Society Press,2013.1-8.
[9] D Zoran,Y Weiss.From learning models of natural image patches to whole image restoration[A].Proceedings of the IEEE International Conference on Computer Vision[C].Barcelona:IEEE Computer Society Press,2011.479-486.
[10] R K ehler,M Hirsch,S Harmeling,B Mohler,B Sch lkopf.Recording and playback of camera shake:benchmarking blind deconvolution with a real-world database[A].Proceedings of the European Conference on Computer Vision[C].Firenze:Springer,2012.157-170.
[11] Y Wang,J Yang,W Yin,Y Zhang.A new alternating minimization algorithm for total variation image reconstruction[J].SIAM J,2008,Imaging Sciences-1(3):248-272.
[12] L Xu,C Lu,Y Xu,J Jia.Image smoothing via L0 gradient minimization[J].ACM Transactions,2011,Graphics-30(6):174-179.
[13] J Pan,Z Hu,Z Su,M Yang.Deblurring text images via L0-regularized intensity and gradient prior[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Columbus:IEEE Computer Society Press,2014.2901-2908.
[14] A Levin,Y Weiss,F Durand,W T Freeman.Efficient marginal likelihood optimization in blind deconvolution[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Providence:IEEE Computer Society Press,2011.2657-2664.
[15] T S Cho,S Paris,B K P Horn,W T Freeman.Blur kernel estimation using the radon transform[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Providence:IEEE Computer Society Press,2011.241-248.
[16] W Lai,J Ding,Y Lin,Y Chuang.Blur kernel estimation using normalized color-line priors[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].Boston:IEEE Computer Society Press,2015.64-72.
[17] O Whyte,J Sivic,A Zisserman.Deblurring shaken and partially saturated images[A].Proceedings of the IEEE International Conference on Computer Vision Workshops[C].Barcelona:IEEE Computer Society Press,2011.745-752.
[18] M Hirsch,C J Schuler,S Harmeling,B Scholkopf.Fast removal of non-uniform camera shake[A].Proceedings of the IEEE International Conference on Computer Vision[C].Barcelona:IEEE Computer Society Press,2011.463-470.
[19] R Fergus,B Singh,A Hertzmann,S T Roweis,W T Freeman.Removing camera shake from a single photograph[J].ACM Transactions,2006,Graphics-25(3):787-794.
[20] T Yue,S Cho,J Wang,Q Dai.Hybrid image deblurring by fusing edge and power spectrum information[A].Proceedings of the European Conference on Computer Vision[C].Zurich:Springer,2014.1-8.

基于模糊结构图的模糊核估计

Blur Kernel Estimation Using Blurry Structure

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	麻文刚, 张亚东, 郭进. 基于景深先验引导与环境光优化的图像去雾[J]. 电子学报, 2022, 50(7): 1708-1721.
[2]	盖杉, 王俊生. 基于深度学习的非局部注意力增强网络图像去雨算法研究[J]. 电子学报, 2020, 48(10): 1899-1908.
[3]	朱江淼, 赵琳潇, 缪京元, 杨洁. 基于光脉冲源的标准脉冲法的宽带取样示波器校准技术研究[J]. 电子学报, 2018, 46(4): 945-951.
[4]	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.
[5]	刘鹏飞, 肖亮. 基于Hessian核范数正则化的快速图像复原算法[J]. 电子学报, 2015, 43(10): 2001-2008.
[6]	徐焕宇, 孙权森, 李大禹, 宣丽. 基于投影的稀疏表示与非局部正则化图像复原方法[J]. 电子学报, 2014, 42(7): 1299-1304.
[7]	吴锡, 周激流, 谢明元. 改进LMMSE的弥散加权磁共振图像Rician噪声复原[J]. 电子学报, 2013, 41(4): 717-721.
[8]	褚宏莉, 李元祥, 周则明, 沈霁. 基于黑色通道的图像快速去雾优化算法[J]. 电子学报, 2013, 41(4): 791-797.
[9]	武鹏飞, 方帅, 徐青山, 饶瑞中. 非均匀大气中单幅退化图像复原[J]. 电子学报, 2013, 41(10): 1895-1902.
[10]	王静, 吕科, 何宁, 王茜. 基于分裂Bregman方法的全变差图像去模糊[J]. 电子学报, 2012, 40(8): 1503-1508.
[11]	刘秀;金伟其;徐超. 基于MPMAP序列红外图像高分辨力重建和非均匀性校正[J]. 电子学报, 2011, 39(9): 2103-2107.
[12]	李亚峰;冯象初. L1投影问题的分裂Bregman方法[J]. 电子学报, 2010, 38(11): 2471-2475.
[13]	方帅;王勇;曹洋;占吉清;饶瑞中. 单幅雾天图像复原[J]. 电子学报, 2010, 38(10): 2279-2284.
[14]	邵文泽;韦志辉. 基于各向异性MRF建模的多帧图像变分超分辨率重建[J]. 电子学报, 2009, 37(6): 1256-1263.
[15]	江玲玲;冯象初;殷海青. 基于Curvelet域的图像复原和分解模型[J]. 电子学报, 2008, 36(9): 1790-1794.