Abstract
In recent years, terahertz (THz) time-domain imaging attracted significant attention and become a useful tool in many applications. A THz time-domain imaging system measures amplitude changes of the THz radiation across a range of frequencies so the absorption coefficient of the materials in the sample can be obtained. THz time-domain images represent 3D hyperspectral cubes with several hundred bands corresponding to different wavelengths i.e., frequencies. Moreover, a THz beam has a non-zero beam waist and therefore introduces band-dependent blurring effects in the resulting images accompanied by system-dependent noise. Removal of blurring effects and noise from the whole 3D hyperspectral cube is addressed in the current work. We will start by introducing THz beam shape effects and its formulation as a deblurring problem, followed by presenting a convolutional neural network (CNN)-based approach which is able to tackle all bands jointly. To the best of our knowledge, this is the first time that a CNN is used to remove the THz beam shape effects from all bands jointly of THz time-domain images. Experiments on synthetic images show that the proposed approach significantly outperforms conventional model-based deblurring methods and band-by-band approaches.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)
Baxter, J.B., Guglietta, G.W.: Terahertz spectroscopy. Anal. Chem. 83(12), 4342–4368 (2011). https://doi.org/10.1021/ac200907z
Bazrafkan, S., Thavalengal, S., Corcoran, P.: An end to end deep neural network for iris segmentation in unconstrained scenarios. Neural Netw. 106, 79–95 (2018). https://doi.org/10.1016/j.neunet.2018.06.011, http://www.sciencedirect.com/science/article/pii/S089360801830193X
Bazrafkan, S., Van Nieuwenhove, V., Soons, J., De Beenhouwer, J., Sijbers, J.: Deep neural network assisted iterative reconstruction method for low dose ct. arXiv preprint arXiv:1906.00650 (2019)
Chan, W.L., Deibel, J., Mittleman, D.M.: Imaging with terahertz radiation. Rep. Prog. Phys. 70(8), 1325–1379 (2007). https://doi.org/10.1088/0034-4885/70/8/r02
Chen, T., et al.: Mxnet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. arXiv preprint arXiv:1512.01274 (2015)
Cosentino, A.: Terahertz and cultural heritage science: examination of art and archaeology. Technologies 4(1) (2016). https://doi.org/10.3390/technologies4010006, https://www.mdpi.com/2227-7080/4/1/6
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007). https://doi.org/10.1109/TIP.2007.901238
Danielyan, A., Katkovnik, V., Egiazarian, K.: BM3D frames and variational image deblurring. IEEE Trans. Image Process. 21(4), 1715–1728 (2012). https://doi.org/10.1109/TIP.2011.2176954
Dhawan, A., Rangayyan, R., Gordon, R.: Image restoration by wiener deconvolution in limited-view computed tomography. Appl. Opt. 24, 4013 (1986). https://doi.org/10.1364/AO.24.004013
Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016). https://doi.org/10.1109/TPAMI.2015.2439281
Duvillaret, L., Garet, F., Coutaz, J.L.: Influence of noise on the characterization of materials by terahertz time-domain spectroscopy. JOSA B 17, 452–461 (2000). https://doi.org/10.1364/JOSAB.17.000452
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (2010)
Guillet, J.P., et al.: Review of terahertz tomography techniques. J. Infrared Millim. Terahertz Waves 35(4), 382–411 (2014). https://doi.org/10.1007/s10762-014-0057-0, https://hal.archives-ouvertes.fr/hal-00968839
Haddad, J.E., Bousquet, B., Canioni, L., Mounaix, P.: Review in terahertz spectral analysis. Trends Anal. Chem. 44, 98–105 (2013). https://doi.org/10.1016/j.trac.2012.11.009, http://www.sciencedirect.com/science/article/pii/S0165993613000022
Hu, B.B., Nuss, M.C.: Imaging with terahertz waves. Opt. Lett. 20(16), 1716–1718 (1995). https://doi.org/10.1364/OL.20.001716, http://ol.osa.org/abstract.cfm?URI=ol-20-16-1716
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Kato, N., et al.: The deep learning vision for heterogeneous network traffic control: proposal, challenges, and future perspective. IEEE Wirel. Commun. 24(3), 146–153 (2016)
Kawase, K., Shibuya, T., Hayashi, S., Suizu, K.: THz Imaging techniques for nondestructive inspections. Comptes Rendus Physique 11(7), 510–518 (2010). https://doi.org/10.1016/j.crhy.2010.04.003, http://www.sciencedirect.com/science/article/pii/S1631070510000423, terahertz electronic and optoelectronic components and systems
Kemp, M.C., Taday, P.F., Cole, B.E., Cluff, J.A., Fitzgerald, A.J., Tribe, W.R.: Security applications of terahertz technology. In: Terahertz for Military and Security Applications, vol. 5070, pp. 44–52 (2003). https://doi.org/10.1117/12.500491, https://doi.org/10.1117/12.500491
Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014)
Krishnan, D., Fergus, R.: Fast image deconvolution using hyper-laplacian priors. Adv. Neural Inf. Process. Syst. 1033–1041 (2009). http://papers.nips.cc/paper/3707-fast-image-deconvolution-using-hyper-laplacian-priors
LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539, https://doi.org/10.1038/nature14539
Lemley, J., Bazrafkan, S., Corcoran, P.: Deep learning for consumer devices and services: pushing the limits for machine learning, artificial intelligence, and computer vision. IEEE Consum. Electron. Mag. 6(2), 48–56 (2017)
Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
Ljubenović., M., Bazrafkan., S., Beenhouwer., J.D., Sijbers., J.: CNN-based deblurring of terahertz images. In: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, pp. 323–330. INSTICC, SciTePress (2020). https://doi.org/10.5220/0008973103230330
Lucy, L.B.: An iterative technique for the rectification of observed distributions. Astron. J. 79(6), 745–754 (1974)
Mallat, S.: A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way, 3rd edn. Academic Press Inc., Orlando, FL, USA (2008)
Mukherjee, S., Federici, J., Lopes, P., Cabral, M.: Elimination of Fresnel reflection boundary effects and beam steering in pulsed terahertz computed tomography. J. Infrared Millim. Terahertz Waves 34(9), 539–555 (2013). https://doi.org/10.1007/s10762-013-9985-3
Pelt, D., Batenburg, K., Sethian, J.: Improving tomographic reconstruction from limited data using mixed-scale dense convolutional neural networks. J. Imaging 4(11), 128 (2018)
Pickwell-MacPherson, E., Wallace, V.P.: Terahertz pulsed imaging - a potential medical imaging modality? Photodiagn. Photodyn. Ther. 6, 128–134 (2009)
Popescu, D.C., Hellicar, A.D.: Point spread function estimation for a terahertz imaging system. EURASIP J. Adv. Signal Process. 2010(1), 575817 (2010). https://doi.org/10.1155/2010/575817, https://doi.org/10.1155/2010/575817
Recur, B., et al.: Propagation beam consideration for 3D THz computed omography. Opt. Express 20(6), 5817–5829 (2012). https://doi.org/10.1364/OE.20.005817, http://www.opticsexpress.org/abstract.cfm?URI=oe-20-6-5817
Richardson, W.H.: Bayesian-based iterative method of image restoration. J. Opt. Soc. Am. 62(1), 55–59 (1972). https://doi.org/10.1364/JOSA.62.000055, http://www.osapublishing.org/abstract.cfm?URI=josa-62-1-55
Shang, C., Yang, F., Huang, D., Lyu, W.: Data-driven soft sensor development based on deep learning technique. J. Process Control 24(3), 223–233 (2014)
Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)
Song, Z., et al.: Temporal and spatial variability of water status in plant leaves by terahertz imaging. IEEE Trans. Terahertz Sci. Technol. 8, 520–527 (2018)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Tao, X., Gao, H., Wang, Y., Shen, X., Wang, J., Jia, J.: Scale-recurrent network for deep image deblurring (2018)
Tepe, J., Schuster, T., Littau, B.: A modified algebraic reconstruction technique taking refraction into account with an application in terahertz tomography. Inverse Probl. Sci. Eng. 25(10), 1448–1473 (2017). https://doi.org/10.1080/17415977.2016.1267168, https://doi.org/10.1080/17415977.2016.1267168
Voulodimos, A., Doulamis, N., Doulamis, A., Protopapadakis, E.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018, 1–13 (2018). https://doi.org/10.1155/2018/7068349
Xu, L., Ren, J.S.J., Liu, C., Jia, J.: Deep Convolutional Neural Network for Image Deconvolution. Adv. Neural Inf. Process. Syst. 27, 1790–1798. Curran Associates, Inc. (2014). http://papers.nips.cc/paper/5485-deep-convolutional-neural-network-for-image-deconvolution.pdf
Xu, L.M., Fan, W., Liu, J.: High-resolution reconstruction for terahertz imaging. Appl. Opt. 53 (2014). https://doi.org/10.1364/AO.53.007891
Zhang, J., et al.: Dynamic scene deblurring using spatially variant recurrent neural networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2521–2529 (2018). https://doi.org/10.1109/CVPR.2018.00267
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). https://doi.org/10.1109/TIP.2017.2662206
Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep cnn denoiser prior for image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3929–3938 (2017)
Zhuang, L., Bioucas-Dias, J.M.: Fast hyperspectral image denoising and inpainting based on low-rank and sparse representations. IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens. 11(3), 730–742 (2018). https://doi.org/10.1109/JSTARS.2018.2796570
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Ljubenović, M., Bazrafkan, S., Paramonov, P., Beenhouwer, J.D., Sijbers, J. (2022). CNN-Based Deblurring of THz Time-Domain Images. In: Bouatouch, K., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2020. Communications in Computer and Information Science, vol 1474. Springer, Cham. https://doi.org/10.1007/978-3-030-94893-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-94893-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-94892-4
Online ISBN: 978-3-030-94893-1
eBook Packages: Computer ScienceComputer Science (R0)