Advertisement

Computational Imaging Method with a Learned Plug-and-Play Prior for Electrical Capacitance Tomography

  • J. LeiEmail author
  • Q. B. Liu
  • X. Y. Wang
Article
  • 72 Downloads

Abstract

Electrical capacitance tomography (ECT) is a potent image-based measurement technology for monitoring industrial processes, but low-quality images generally limit its application scope and measurement reliability. To increase the precision of reconstruction, in this study, a data-driven plug-and-play prior abstracted by a deep convolutional neural network (DCNN) and the sparseness prior of imaging objects, in form of regularizers, are jointly leveraged to generate a potent imaging model, in which the L1 norm of the mismatch error acts as a data fidelity term (DFT) to weaken the sensitivity of estimation result to noisy input data. The DCNN is embedded into the split Bregman (SB) technique to generate a powerful computing scheme for solving the built imaging model and the fast iterative shrinkage-thresholding algorithm (FISTA) is applied to solve the sub-problems efficiently. Extensive numerical results verify that the proposed imaging technique has competitive reconstruction ability and better robustness in comparison with the state-of-the-art methods. This study demonstrates the validity and efficacy of the proposed algorithm in reducing reconstruction error. Most importantly, the research outcomes verify that the data-driven plug-and-play prior and the sparseness prior can be jointly embedded into the imaging model, leading to a remarkable decline in reconstruction error.

Keywords

Image reconstruction Deep convolutional neural network Image prior Data-driven prior Inverse problem Electrical capacitance tomography 

Notes

Funding Information

This study was funded by the Fundamental Research Funds for the Central Universities (no. 2017MS012), the National Natural Science Foundation of China (nos. 51206048 and 51576196), and the National Key Research and Development Program of China (no. 2017YFB0903601).

Compliance with Ethical Standards

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. 1.
    Tikhonov AN, Arsenin VY. Solution of ill-posed problems. New York: V.H. Winston & Sons; 1977.Google Scholar
  2. 2.
    Liu S, Fu L, Yang WQ, Wang HG, Jiang F. Prior-online iteration for image reconstruction with electrical capacitance tomography. IEE Proc: Sci Meas Technol. 2004;151:195–200.Google Scholar
  3. 3.
    Landweber L. An iteration formula for Fredholm integral equations of the first kind. Am J Math. 1951;73:615–24.CrossRefGoogle Scholar
  4. 4.
    Yan H, Wang YF, Zhou YG, Sun YH. 3D ECT reconstruction by an improved Landweber iteration algorithm. Flow Meas Instrum. 2014;37:92–8.CrossRefGoogle Scholar
  5. 5.
    Guo G, Tong GW, Lu L, Liu S. Iterative reconstruction algorithm for the inverse problems in electrical capacitance tomography. Flow Meas Instrum. 2018;64:204–12.CrossRefGoogle Scholar
  6. 6.
    Arrabal-Campos FM, Aguilera-Sáez LM, Fernández I. Algebraic reconstruction technique for diffusion NMR experiments. Application to the molecular weight prediction of polymers. J Phys Chem A. 2019;123:943–50.CrossRefGoogle Scholar
  7. 7.
    Dong XY, Ye ZY, Soleimani M. Image reconstruction for electrical capacitance tomography by using soft-thresholding iterative method with adaptive regulation parameter. Meas Sci Technol. 2013;24:1–8.CrossRefGoogle Scholar
  8. 8.
    Wang HC, Fedchenia I, Shishkin SL, Finn A, Smith LL, Colket M. Sparsity-inspired image reconstruction for electrical capacitance tomography. Flow Meas Instrum. 2015;43:59–71.CrossRefGoogle Scholar
  9. 9.
    Ye JM, Wang HG, Yang WQ. Image reconstruction for electrical capacitance tomography based on sparse representation. IEEE Trans Instrum Meas. 2015;64:89–102.CrossRefGoogle Scholar
  10. 10.
    Hosani EA, Zhang M, Abascal J, Soleimani M. Imaging metallic samples using electrical capacitance tomography: forward modelling and reconstruction algorithms. Meas Sci Technol. 2016;27:1–11.CrossRefGoogle Scholar
  11. 11.
    Frias MAR, Yang WQ. Real-time model-based image reconstruction with a prior calculated database for electrical capacitance tomography. Meas Sci Technol. 2017;28:1–14.Google Scholar
  12. 12.
    Hosani EA, Soleimani M. Multiphase permittivity imaging using absolute value electrical capacitance tomography data and a level set algorithm. Proceedings of the Royal Society A: Mathematical Physical and Engineering Sciences. 2017;374:20150332.  https://doi.org/10.1098/rsta.2015.0332.CrossRefGoogle Scholar
  13. 13.
    Xia C, Su C, Cao J, Li P. Reconstruction of electrical capacitance tomography images based on fast linearized alternating direction method of multipliers for two-phase flow system. Chin J Chem Eng. 2016;24:597–605.CrossRefGoogle Scholar
  14. 14.
    Wang P, Lin JS, Wang M. An image reconstruction algorithm for electrical capacitance tomography based on simulated annealing particle swarm optimization. J Appl Res Technol. 2015;13:197–204.CrossRefGoogle Scholar
  15. 15.
    Taylor SH, Garimella SV. Shape-energy evolutionary reconstruction algorithm for electrical capacitance tomography in a high-aspect-ratio domain. Sensors Actuators A Phys. 2015;233:349–59.CrossRefGoogle Scholar
  16. 16.
    Wu X, Huang G, Wang J, Xu C. Image reconstruction method of electrical capacitance tomography based on compressed sensing principle. Meas Sci Technol. 2013;24:1–7.Google Scholar
  17. 17.
    Soleimani M, Lionheart WRB. Nonlinear image reconstruction for electrical capacitance tomography using experimental data. Meas Sci Technol. 2005;16:1987–96.CrossRefGoogle Scholar
  18. 18.
    Chen J, Zhang M, Liu Y, Chen J, Li Y. Image reconstruction algorithms for electrical capacitance tomography based on ROF model using new numerical techniques. Meas Sci Technol. 2017;28:1–11.Google Scholar
  19. 19.
    Haddadi MB, Maddahian R. A new algorithm for image reconstruction of electrical capacitance tomography based on inverse heat conduction problems. IEEE Sensors J. 2016;16:1786–94.CrossRefGoogle Scholar
  20. 20.
    Lei J, Liu WY, Liu QB, Wang XY, Liu S. Robust dynamic inversion algorithm for the visualization in electrical capacitance tomography. Measurement. 2014;50:305–18.CrossRefGoogle Scholar
  21. 21.
    Lei J, Mu HP, Liu QB, Wang XY, Liu S. Data-driven reconstruction method for electrical capacitance tomography. Neurocomputing. 2018;273:333–45.CrossRefGoogle Scholar
  22. 22.
    Zhao JY, Xu LJ, Cao Z. Direct image reconstruction for electrical capacitance tomography using shortcut D-Bar method. IEEE Trans Instrum Meas. 2019;68:483–92.CrossRefGoogle Scholar
  23. 23.
    Martin R, Ogarko V, Komatitsch D, Jessell M. Parallel three-dimensional electrical capacitance data imaging using a nonlinear inversion algorithm and L p norm-based model regularization. Measurement. 2018;128:428–45.CrossRefGoogle Scholar
  24. 24.
    Yang WQ, Peng LH. Image reconstruction algorithms for electrical capacitance tomography. Meas Sci Technol. 2003;14:R1–R13.CrossRefGoogle Scholar
  25. 25.
    Jin Z, Zhou G, Gao D, Zhang Y. EEG classification using sparse Bayesian extreme learning machine for brain-computer interface. Neural Comput & Applic. 2018.  https://doi.org/10.1007/s00521-018-3735-3.
  26. 26.
    Zhang Y, Wang Y, Zhou G, Jin J, Wang B, Wang X, et al. Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces. Expert Syst Appl. 2018;96:302–10.CrossRefGoogle Scholar
  27. 27.
    Jiao Y, Zhang Y, Wang Y, Wang B, Jin J, Wang X. A novel multilayer correlation maximization model for improving CCA-based frequency recognition in SSVEP brain-computer interface. Int J Neural Syst. 2018;28:1–14.CrossRefGoogle Scholar
  28. 28.
    Wang R, Zhang Y, Zhang L. An adaptive neural network approach for operator functional state prediction using psychophysiological data. Integrated Computer-Aided Engineering. 2015;23:81–97.CrossRefGoogle Scholar
  29. 29.
    Liu N, Wan L, Zhang Y, Zhou T, Huo H, Fang T. Exploiting convolutional neural networks with deeply local description for remote sensing image classification. IEEE Access. 2018;6:11215–28.CrossRefGoogle Scholar
  30. 30.
    Lan X, Zhang S, Yuen PC, Chellappa R. Learning common and feature-specific patterns: a novel multiple-sparse-representation-based tracker. IEEE Trans Image Process. 2018;27:2022–37.CrossRefGoogle Scholar
  31. 31.
    Lan X, Ma AJ, Yuen PC, Chellappa R. Joint sparse representation and robust feature-level fusion for multi-cue visual tracking. IEEE Trans Image Process. 2015;24:5826–41.CrossRefGoogle Scholar
  32. 32.
    Lan X, Ma AJ, Yuen PC. Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation. IEEE Conference on Computer Vision and Pattern Recognition. 2014; pp. 1194–1201.  https://doi.org/10.1109/cvpr.2014.156.
  33. 33.
    Lan X, Ye M, Zhang S, Zhou H, Yuen PC. Modality-correlation-aware sparse representation for RGB infrared object tracking. Pattern Recogn Lett. 2018.  https://doi.org/10.1016/j.patrec.2018.10.002.
  34. 34.
    Feng S, Wang Y, Song K, Wang D, Yu G. Detecting multiple coexisting emotions in microblogs with convolutional neural networks. Cogn Comput. 2017;10:136–55.CrossRefGoogle Scholar
  35. 35.
    Li R, Gu D, Liu Q, Long Z, Hu H. Semantic scene mapping with spatio-temporal deep neural network for robotic applications. Cogn Comput. 2017;10:260–71.CrossRefGoogle Scholar
  36. 36.
    Ren P, Sun W, Luo C, Hussain A. Clustering-oriented multiple convolutional neural networks for single image super-resolution. Cogn Comput. 2017;10:165–78.CrossRefGoogle Scholar
  37. 37.
    Aljarah I, Al-Zoubi AM, Faris H, Hassonah MA, Mirjalili S, Saadeh H. Simultaneous feature selection and support vector machine optimization using the grasshopper optimization algorithm. Cogn Comput. 2018;10:478–95.CrossRefGoogle Scholar
  38. 38.
    Huang GB. What are extreme learning machines? Filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle. Cogn Comput. 2015;7:263–78.CrossRefGoogle Scholar
  39. 39.
    Lan X, Ye M, Shao R, Zhong B, Yuen PC, Zhou H. Learning modality-consistency feature templates: a robust RGB-infrared tracking system. IEEE Trans Ind Electron. 2019;66:9887–97.  https://doi.org/10.1109/tie.2019.2898618.CrossRefGoogle Scholar
  40. 40.
    Lan XY, Ye M, Shao R, Zhong B, Jain DK, Zhou HY. Online non-negative multi-modality feature template learning for RGB-assisted infrared tracking. IEEE Access. 2019;7:67761–71.CrossRefGoogle Scholar
  41. 41.
    Yang XS, Deb S, Mishra SK. Multi-species cuckoo search algorithm for global optimization. Cogn Comput. 2018;10:1085–95.CrossRefGoogle Scholar
  42. 42.
    Zeng NY, Wang ZD, Zhang H, Alsaadi FE. A novel switching delayed PSO algorithm for estimating unknown parameters of lateral flow immunoassay. Cogn Comput. 2016;8:143–52.CrossRefGoogle Scholar
  43. 43.
    Goldstein T, Osher S. The split Bregman method for L1-regularized problems. SIAM J Imag Sci. 2009;2:323–43.CrossRefGoogle Scholar
  44. 44.
    Boyd S, Parikh N, Chu E, Peleato B, Eckstein J. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine Learning. 2011;3:1–122.CrossRefGoogle Scholar
  45. 45.
    Beck A, Teboulle M. A fast iterative shrinkage/thresholding algorithm for linear inverse problems. SIAM J Imag Sci. 2009;2:183–202.CrossRefGoogle Scholar
  46. 46.
    Hale ET, Yin WT, Zhang Y. Fixed-point continuation for L1-minimization: methodology and convergence. SIAM J Optim. 2008;19:1107–30.CrossRefGoogle Scholar
  47. 47.
    Hao BB, Zhu JG. Fast L1 regularized iterative forward backward splitting with adaptive parameter selection for image restoration. J Vis Commun Image Represent. 2017;44:139–47.CrossRefGoogle Scholar
  48. 48.
    Chambolle A, Pock T. A first-order primal-dual algorithm for convex problems with applications to imaging. J Math Imaging Vision. 2011;40:120–45.CrossRefGoogle Scholar
  49. 49.
    Figueiredo M, Nowak R, Wright SJ. Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems. IEEE J Sel Top Sign Process. 2007;1:586–97.CrossRefGoogle Scholar
  50. 50.
    Li SJ, Qi HR. A Douglas-Rachford splitting approach to compressed sensing image recovery using low-rank regularization. IEEE Trans Image Process. 2015;24:4240–9.CrossRefGoogle Scholar
  51. 51.
    Yun S, Toh KC. A coordinate gradient descent method for L1-regularized convex minimization. Comput Optim Appl. 2011;48:273–307.CrossRefGoogle Scholar
  52. 52.
    Candès EJ, Wakin MB, Boyd SP. Enhancing sparsity by reweighted L1 minimization. J Fourier Anal Appl. 2008;14:877–905.CrossRefGoogle Scholar
  53. 53.
    Venkatakrishnan S, Bouman C, Wohlberg B. Plug-and-play priors for model based reconstruction. IEEE Global Conference on Signal and Information Processing 2013; pp. 945–948.Google Scholar
  54. 54.
    Chan SH, Wang X, Elgendy OA. Plug-and-play ADMM for image restoration: fixed point convergence and applications. IEEE Transactions on Computational Imaging. 2017;3:84–98.CrossRefGoogle Scholar
  55. 55.
    Rond A, Giryes R, Elad M. Poisson inverse problems by the plug-and-play scheme. J Vis Commun Image Represent. 2016;41:96–108.CrossRefGoogle Scholar
  56. 56.
    Zhang K, Zuo W, Gu S, Zhang L. Learning deep CNN denoiser prior for image restoration. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017; pp. 2808–2817.Google Scholar
  57. 57.
    Brifman A, Romano Y, Elad M. Turning a denoiser into a superresolver using plug and play priors. IEEE International Conference on Image Processing (ICIP) 2016; pp. 1404–1408.Google Scholar
  58. 58.
    Isaac Y, Barthélemy Q, Gouy-Pailler C, Sebag M, Atif J. Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations. Signal Process. 2017;130:389–402.CrossRefGoogle Scholar
  59. 59.
    Gopi VP, Palanisamy P, Wahid KA, Babyn P, Cooper D. Multiple regularization based MRI reconstruction. Signal Process. 2014;103:103–13.CrossRefGoogle Scholar
  60. 60.
    Wang Q, Wu Z, Jin J, Wang T, Shen Y. Low rank constraint and spatial spectral total variation for hyperspectral image mixed denoising. Signal Process. 2018;142:11–26.CrossRefGoogle Scholar
  61. 61.
    Zhang Z, Xiahou J, Bai ZJ, Hancock ER, Zhou D, Chen SB, et al. Discriminative Lasso. Cogn Comput. 2016;8:847–55.CrossRefGoogle Scholar
  62. 62.
    Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge: MIT Press; 2016.Google Scholar
  63. 63.
    Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 2006;313:504–7.CrossRefGoogle Scholar
  64. 64.
    Bengio Y. Learning deep architectures for AI. Foundations and Trends® in Machine Learning. 2009;2:1–127.CrossRefGoogle Scholar
  65. 65.
    LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–44.CrossRefGoogle Scholar
  66. 66.
    Liu XL, Deng ZD. Segmentation of drivable road using deep fully convolutional residual network with pyramid pooling. Cogn Comput. 2016;10:272–81.CrossRefGoogle Scholar
  67. 67.
    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–8.CrossRefGoogle Scholar
  68. 68.
    Li YJ, Zhang T. An introduction to deep learning and case analysis. Beijing: China Machine Press; 2016.Google Scholar
  69. 69.
    LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86:2278–324.CrossRefGoogle Scholar
  70. 70.
    He XP, Liu B. Deep learning: theory and practice. Beijing: Science Press; 2017.Google Scholar
  71. 71.
    Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process. 2017;26:3142–55.CrossRefGoogle Scholar
  72. 72.
    Li JP, Zhang ZX, He HG. Hierarchical convolutional neural networks for EEG-based emotion recognition. Cogn Comput. 2018;10:368–80.CrossRefGoogle Scholar
  73. 73.
    Wang YF. Computing methods for inverse problems and their applications. Beijing: Higher Education Press; 2007.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Energy, Power and Mechanical EngineeringNorth China Electric Power UniversityBeijingChina
  2. 2.Institute of Engineering ThermophysicsChinese Academy of SciencesBeijingChina
  3. 3.School of Control and Computer EngineeringNorth China Electric Power UniversityBeijingChina

Personalised recommendations