Abstract
It is proposed that neural networks be used to solve the problem of flat-field correction. A process is described for selecting parameters of a deep convolutional neural network in order to solve the problem of flat-field correction with the instability of an empty beam, training this network, and checking its operability on the generated data. The procedure is tested on data obtained with laboratory X-ray and synchrotron sources.
REFERENCES
Landis, E.N. and Keane, D.T., Mater. Charact., 2010, vol. 61, no. 12, p. 1305.
Seibert, J.A., Boone, J.M., and Lindfors, K.K., Proc. SPIE, 1998, vol. 3336, p. 348.
Nieuwenhove, V.V., Beenhouwer, J.D., Carlo, F.D., et al., Opt. Express, 2015, vol. 23, no. 21, p. 27975.
Hagemann, J., Vassholz, M., Hoeppe, H., et al., J. Synchrotron Radiat., 2021, vol. 28, no. 1, p. 52.
Buakor, K., Zhang, Yu., Birnšteinová, Š., et al., Opt. Express, 2022, vol. 30, no. 7, p. 10633.
LeCun, Y., Bengio, Y., and Hinton, G., Nature, 2015, vol. 521, no. 7553, p. 436.
van Dyk, D.A. and Meng, X.L., J. Comput. Gr. Stat., 2001, vol. 10, no. 1, p. 1.
Buzmakov, A.V., Asadchikov, V.E., Zolotov, D.A., et al., Crystallogr. Rep., 2018, vol. 63, no. 6, p. 1057.
Tlustos, L., Campbell, M., Heijne, E., and Llopart, X., Proc. 2003 IEEE Nuclear Science Symposium, vol. 3, Portland, 2003, p. 1588.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al., Advances in Neural Information Processing Systems, vol. 27, Montreal, 2014, p. 1.
Ronneberger, O., Fischer, P., and Brox, Th., Proc. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Munich, 2015, p. 1.
Ledig, C., Theis, L., Huszar, F., et al., Proc. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, 2017, p. 4681.
Wang, L.T., Hoover, N.E., Porter, E.H., and Zasio, J.J., Proc. 24th ACM/IEEE Design Automation Conference, Miami Beach, 1987, p. 2.
Ruder, S., arXiv:1609.04747, 2016.
Funding
The study was supported by the RF Ministry of Science and Higher Education within the framework of the state task of the Federal Research Center “Crystallography and Photonics” of the Russian Academy of Sciences in terms of the interpretation of tomographic data. The work on carrying out tomographic measurements was carried out with the support of the RF Ministry of Science and Higher Education as part of the work under grant no. 075-15-2021-1362.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by N. Petrov
About this article
Cite this article
Grigorev, A.Y., Buzmakov, A.V. Flat-Field Correction of X-Ray Tomographic Images Using Deep Convolutional Neural Networks. Bull. Russ. Acad. Sci. Phys. 87, 604–610 (2023). https://doi.org/10.3103/S1062873822701684
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1062873822701684