基于卷积稀疏编码的电容层析成像图像重建

doi:10.3969/j.issn.1000-1158.2023.07.11

PDF(42630 KB)

计量学报 ›› 2023, Vol. 44 ›› Issue (7) : 1075-1079. DOI: 10.3969/j.issn.1000-1158.2023.07.11

流量计量

基于卷积稀疏编码的电容层析成像图像重建

张立峰,卢栋臣

作者信息 +

Image Reconstruction for Electrical Capacitance Tomography Based on Convolutional Sparse Coding

ZHANG Li-feng,LU Dong-chen

Author information +

文章历史 +

摘要

针对电容层析成像(ECT)病态性逆问题,提出了一种将卷积稀疏编码模型作为惩罚项嵌入到ECT最小二乘问题的方法,通过预先训练好的滤波器并结合交替方向乘子算法(ADMM)对此模型进行求解,从而完成ECT图像重建。对提出的方法进行了仿真及实验测试,并与LBP、Tikhonov正则化及Landweber迭代算法进行比较。结果表明,提出的方法其重建图像平均相对误差和相关系数分别为0.438 9及0.8968,均优于其他3种方法,中心物体及多物体分布的重建质量得到显著提升。

Abstract

Aiming at the ill-conditioned inverse problem of electrical capacitance tomography (ECT), a method of introducing convolution sparse coding model into ECT least squares problem as penalty is proposed. The model is solved by pre-trained filter and alternating direction method of multipliersr algorithm (ADMM), and the ECT image reconstruction is completed. The proposed method is simulated and tested experimentally, and compared with LBP, Tikhonov regularization and Landweber iterative algorithm. The results show that the average relative error and correlation coefficient of the reconstructed image obtained by the proposed method are 0.4389 and 0.8968, respectively, which are superior to the other three methods, and the reconstruction quality of central object and multi-object distribution is significantly improved.

导出引用

张立峰卢栋臣. 基于卷积稀疏编码的电容层析成像图像重建[J]. 计量学报. 2023, 44(7): 1075-1079 https://doi.org/10.3969/j.issn.1000-1158.2023.07.11

ZHANG Li-feng,LU Dong-chen. Image Reconstruction for Electrical Capacitance Tomography Based on Convolutional Sparse Coding[J]. Acta Metrologica Sinica. 2023, 44(7): 1075-1079 https://doi.org/10.3969/j.issn.1000-1158.2023.07.11

中图分类号： TB937

参考文献

［1］王化祥.电学层析成像［M］.北京: 科学出版社,2013.
［2］赵玉磊, 郭宝龙, 闫允一. 电容层析成像技术的研究进展与分析［J］.仪器仪表学报, 2012, 33(8):1909-1920.
Zhao Y L, Guo B L, Yan Y Y. Research progress and analysis of electrical capacitance tomography［J］. Journal of Instrumentation, 2012,33(8):1909-1920.
［3］赵愉, 岳士弘, 张洋洋, 等. 航空发动机中气液两相流的可视化检测［J］. 北京航空航天大学学报, 2017, 43(11):2345-2351.
Zhao Y, Yue S H, Zhang Y Y, et al. Visual detection of gas-liquid two-phase flow in aeroengine［J］. Journal of Beihang University, 2017,43 (11):2345-2351.
［4］张立峰, 朱炎峰. 极限学习机在电容层析成像中的应用［J］. 电测与仪表, 2020, 57(9):146-152.
Zhang L F, Zhu Y F. Application of Extreme Learning Machine in Electrical Capacitance Tomography［J］. Electrical Measurement and Instrument, 2020, 57(9):
146-152.
［5］马敏, 孙美娟. 基于改进线性Bregman算法的ECT图像重建算法［J］. 计量学报, 2021, 42(7):879-884.
Ma M, Sun M J. ECT image reconstruction algorithm based on improved linear Bregman algorithm［J］. Acta Metrologica Sinica, 2021,42(7):879-884.
［6］Lustig M, Donoho D, Pauly J M. Sparse MRI:the application of compressed sensing for rapid MR imaging［J］. Magnetic Resonance in Medicine, 2007, 58(8):1182-1195.
［7］张立峰, 刘昭麟, 田沛. 基于压缩感知的电容层析成像图像重建算法［J］. 电子学报, 2017, 45(2):353-358.
Zhang L F, Liu Z L, Tian P. Image reconstruction algorithm of electrical capacitance tomography based on compressive sensing［J］. Journal of Electronics, 2017,45(2):353-358.
［8］王琦, 张荣华, 王金海, 等. 基于压缩感知的ECT/CT双模融合系统成像方法［J］.仪器仪表学报, 2014, 35(6):1338-1346.
Wang Q, Zhang R H, Wang J H, et al. Imaging method of ECT/CT dual-mode fusion system based on compressed sensing［J］. Chinese Journal of Scientific Instrument, 2014,35(6):1338-1346.
［9］Ye J M, Wang H G, Yang W Q. Image Reconstruction for Electrical Capacitance Tomography Based on Sparse Representation［J］. IEEE Transactions on Instrumentation and Measurement, 2015,64(1):89-102.
［10］马敏, 刘一斐,刘亚楠. 基于改进半阈值迭代算法的ECT图像重建［J］. 计量学报, 2021,42(5):595-602.
Ma M, Liu Y F, Liu Y N. ECT Image Reconstruction Based on Improved Half-threshold Iterative Algorithm［J］.
Acta Metrologica Sinica, 2021,42(5):595-602.

［11］李雨, 史娜, 孔慧华. 基于全变分和梯度域卷积稀疏编码的稀疏角度CT重建算法［J］. 激光与光电子学进展, 2021, 58(12):339-348.
Li L, Shi N, Kong H H. Sparse angle CT reconstruction algorithm based on total variation and gradient domain convolutional sparse coding ［J］. Advances in Laser and Optoelectronics, 2021,58(12):339-348.
［12］Zeiler M, Krishnan D, Taylor G, et al. Deconvolutional networks［C］//Proceedings of the 2010 IEEE Computer Society Conference on computer vision and pattern recognition. IEEE, 2010:2528-2535.
［13］Bao P, Xia W J, Yang K, et al.Convolutional Sparse Coding for Compressd Sensing CT Reconstruction［J］. IEEE Transactions on Medical Imaging, 2019,38(11):2607-2619.
［14］韩娟娟. 面向张量卷积稀疏编码的结构化滤波器学习及其应用［D］. 石家庄:河北师范大学, 2021.
［15］陈楠, 张标. 多尺度半耦合卷积稀疏编码的遥感影像超分辨率重建［J］.计算机辅助设计与图形学学报, 2022, 34(3):382-391.
Chen N, Zhang B. Super-resolution reconstruction of remote sensing images with multi-scale semi-coupled convolutional sparse coding ［J］. Journal of Computer Aided Design and Graphics, 2022,34(3):382-391.
［16］王丁东. 基于弱监督学习的医学图像跨模态超分辨率重建方法研究［D］. 成都:电子科技大学,2020.
［17］张立峰, 张明. 一种电容层析成像图像重建优化算法［J］.计量学报, 2021,42(9):1155-1159.
Zhang L F, Zhang M. An optimization algorithm of electrical capacitance tomography image reconstruction［J］. Acta Metrologica Sinica, 2021,42(9):1155-1159.