基于块稀疏的电阻抗成像算法

王琦; 张鹏程; 汪剑鸣; 李秀艳; 连志杰; 陈庆良; 陈彤云; 陈晓静; 贺静; 段晓杰; 王化祥

doi:10.11999/JEIT170425

基于块稀疏的电阻抗成像算法

doi: 10.11999/JEIT170425

2.
(天津市胸科医院　天津　300000)
3.
(天津大学电气与自动化工程学院天津 300072)

基金项目:

国家科技支撑计划重点项目(2013BAF06B00)，国家自然科学基金(61601324, 61373104, 61402330, 61405143)，天津市应用基础与前沿技术研究计划(15JCQNJC01500)

计量
- 文章访问数: 1304
- HTML全文浏览量: 126
- PDF下载量: 166
- 被引次数: 42
出版历程
- 收稿日期: 2017-05-09
- 修回日期: 2017-12-15
- 刊出日期: 2018-03-19

Block-Sparse Reconstruction for Electrical Impedance Tomography

2.
(Tianjin Chest Hospital, Tianjin 300000, China)
3.
(School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072, China)

Funds:

The Key Projects of National Science and Technology Support Program (2013BAF06B00), The National Natural Science Foundation of China (61601324, 61373104, 61402330, 61405143), The Natural Science Foundation of Tianjin Municipal Science and Technology Commission (15JCQNJC01500)

摘要

摘要: 该文提出一种基于自适应块稀疏字典学习的电阻抗图像重建算法，构建了分块稀疏字典，较好地保留了重建图像的细节信息；同时，将字典学习与图像重建交替进行，并将迭代重建的中间结果作为稀疏字典的训练样本，有效提高了字典学习效果。数值仿真与实验重建结果表明，新方法对电阻抗成像系统测量噪声具有较好的鲁棒性，能准确重构电导率分布图像，特别是对突变细节的准确恢复。
- 电阻抗层析成像 /
- 图像重建 /
- 稀疏表示 /
- 字典学习
Abstract: An electrical impedance image reconstruction algorithm based on adaptive block-sparse dictionary is proposed. A block-sparse dictionary is constructed creatively, which preferably preserves the details of reconstructed images. Meanwhile, the sparsifying dictionary optimization and image reconstruction are performed alternately, and the intermediate result of the iterative reconstruction is used as the training sample of the sparse dictionary, which can effectively improve the learning effect of the dictionary. The numerical simulation and experiment results show that the patch-based sparsity method for measure noise has excellent robustness and can accurately reconstruct the conductivity distribution image, especially the precise details of mutation.
- Electrical impedance tomography /
- Image reconstruction /
- Sparse representation /
- Dictionary learning

HTML全文

参考文献(15)

WANG Q, LIAN Z, WANG J, et al. Accelerated reconstruction of electrical impedance tomography images via patch based sparse representation[J]. Review of Scientific Instruments, 2016, 87(11): 114707, doi: 10.1063/1.4966998.

SBARBARO D, VAUHKONEN M, and JOHANSEN T A. State estimation and inverse problems in electrical impedance tomography: observability, convergence and regularization[J]. Inverse Problems, 2015, 31(4): 045004, doi: 10.1088/0266- 5611/31/4/045004.

Ye J, WANG H, and YANG W. Image reconstruction for electrical capacitance tomography based on sparse representation[J]. IEEE Transactions on Instrumentation Measurement, 2015, 64(1): 89-102. doi: 10.1109/TIM.2014. 2329738.

LIU Y, YANG Z, and YANG L. Online signature verification based on DCT and sparse representation[J]. IEEE Transactions on Cybern, 2015, 45(11): 2498-2511. doi: 10.1109/TCYB.2014.2375959.

NAZZAL M and OZKARAMANLI H. Wavelet domain dictionary learning-based single image superresolution[J]. Signal, Image and Video Processing, 2015, 1(7): 1-11. doi: 10.1007/s11760-013-0602-7.

WIECZOREK M, FRIKEL J, VOGEL J, et al. X-ray computed tomography using curvelet sparse regularization[J]. Medical Physics, 2015, 42(4): 1555-1567. doi: 10.1118/ 1.4914368.

LIU Y, LIU S, and WANG Z. A general framework for image fusion based on multi-scale transform and sparse representation[J]. Information Fusion, 2015, 24: 147-164. doi: 10.1016/j.inffus.2014.09.004.

GARDE H and KNUDSEN K. Sparsity prior for electrical impedance tomography with partial data[J]. Inverse Problems in Science and Engineering, 2016(3): 524-541. doi: 10.1080/17415977.2015.1047365.

JIN B, KHAN T, and MAASS P. A reconstruction algorithm for electrical impedance tomography based on sparsity regularization[J]. International Journal for Numerical Methods in Engineering, 2012, 89(3): 337-353. doi: 10.1002 /nme.3247.

WANG Q, WANG H, ZHANG R, et al. Image reconstruction based on L1 regularization and projection methods for electrical impedance tomography[J]. Review of Scientific Instruments, 2012, 83(10): 104707. doi: 10.1063/1.4760253.

YUE B, WANG S, LIANG X, et al. Robust coupled dictionary learning with 1-norm coefficients transition constraint for noisy image super-resolution[J]. Signal Processing, 2017, 140: 177-189. doi: 10.1016/j.sigpro.2017. 04.015.

QU X, HOU Y, LAM F, et al. Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator[J]. Medical Image Analysis, 2014, 18(6): 843-856. do: 10.1016/j.media.2013.09.007.

HEMMING B, FAGERLUND A, and LASSILA A. Linearized solution to electrical impedance tomography based on the Schur conjugate gradient method[J]. Measurement Science Technology, 2007, 18(11): 3373-3383. doi: 10.1088/0957-0233/18/11/017.

WANG M. Inverse solutions for electrical impedance tomography based on conjugate gradients methods[J]. Measurement Science Technology, 2001, 13(1): 101-117. doi: 10.1088/0957-0233/13/1/314.

BAO C, CAI J F, and JI H. Fast sparsity-based orthogonal dictionary learning for image restoration[C]. IEEE International Conference on Computer Vision IEEE, Sydney, 2014: 3384-3391. doi: 10.1109/ICCV.2013.420.

施引文献

期刊类型引用(9)

1.	张睿敏，张甲艳，陶冶. 变分贝叶斯估计图像滤波去噪算法. 计算机技术与发展. 2021(07): 59-63 . 百度学术
2.	郑恩，成耀天，林靖宇. 采用去抖动模糊算法的稠密三维重建. 计算机工程与应用. 2018(01): 217-223 . 百度学术
3.	仇翔，戴明. 基于L0稀疏先验的相机抖动模糊图像盲复原. 光学精密工程. 2017(09): 2490-2498 . 百度学术
4.	闫敬文，谢婷婷，彭鸿，刘攀华. 基于L_0范数正则项的运动图像去模糊. 激光与光电子学进展. 2017(02): 156-163 . 百度学术
5.	杨亚威，李俊山，张士杰，芦鸿雁，胡双演. 基于视觉对比敏感度与恰可察觉失真感知的图像复原. 光学精密工程. 2014(02): 459-466 . 百度学术
6.	阮光诗，孙俊喜，孙阳，刘红喜，赵立荣，刘广文. 处理异常值的相机抖动模糊图像复原. 中国图象图形学报. 2014(05): 677-682 . 百度学术
7.	吴庆，肖力，孙志刚. 基于运动检测的图像去模糊算法. 计算机与现代化. 2013(12): 110-113 . 百度学术
8.	杨敬娴，郭喜庆，孙鹏飞，韩文钦，解官宝. 集成学习法与双分裂Bregman正则化下的图像复原. 微电子学与计算机. 2013(12): 85-89+96 . 百度学术
9.	李绍春，初永玲，王枚. 三维旋转运动模糊图像的复原方法研究. 赤峰学院学报(自然科学版). 2012(20): 22-24 . 百度学术