• 2024 (Vol.38)
  • 1990 (Vol.4)
  • 1989 (Vol.3)
  • 1988 (Vol.2)
  • 1987 (Vol.1)

Volume 35 #4

Contents

  1. Age-related difference in perception of aesthetics and visual complexity of graphical user interfaces
  2. Theoretical analysis of factors that determine features of visual attention in preterm children
  3. Differentiation of Reasoning Processes Based on Eye Movement Indicators
  4. Interaction of foveal and peripheral vision in the implementation of systemic visual functions
  5. Generation of synthetic porous images for data augmentation to train machine learning algorithms

Generation of synthetic porous images for data augmentation to train machine learning algorithms

© 2021 А. V. Khafizova, M. V. Grigorievb

aFSRC Crystallography and photonics RAS 119333 Moscow, Leninskiy Prospekt, 59, Russia
bInstitute of Microelectronics Technology and High-Purity Materials of the RAS, 142432 Chernogolovka, Ulitsa Akademika Osip'yana, 6, Russia

Received 09 Jun 2021

The technique of the parameter calculations for the porous structure generator from experimental images to synthesize the porous phantoms is presented. The phantoms generated by the found parameters have geometric characteristics similar to the original images, which makes it possible to use such phantoms as augmentation of training dataset for the segmentation of experimental images using machine learning methods.

Key words: computed tomography, transfer learning, augmentation, synthetic data

DOI: 10.31857/S023500922104003X

Cite: Khafizov А. V., Grigoriev M. V. Generirovanie sinteticheskikh poristykh izobrazhenii dlya augmentatsii dannykh s tselyu trenirovki algoritmov mashinnogo obucheniya [Generation of synthetic porous images for data augmentation to train machine learning algorithms]. Sensornye sistemy [Sensory systems]. 2021. V. 35(4). P. 340–347 (in Russian). doi: 10.31857/S023500922104003X

References:

  • Grigoriev M.V., Nazirov I.V., Mogilevskiy E.I., Khafizov A.V., Chukalina M.V. O problemakh pri rabote s mikrotomograficheskimi izobrazheniyami poristykh struktur, ispol'zuemymi dlya modelirovaniya protsessov protekaniya [About problems when working with micro tomographic images of porous structures used for modeling flow processes]. Trudy instituta sistemnogo analiza rossiiskoi akademii nauk [Proceedings of the Institute of System Analysis of the Russian Academy of Sciences]. 2021. V. 71 (1). https://doi.org/10.14357/20790279210110.
  • Khafizov A.V., Grigoriev M.V., Metod logisticheskoi regressii dlya binarizatsii tomograficheskikh izobrazhenii poristykh ob''ektov [Logistic regression method for binarization of tomographic images of porous objects]. Sovremennye metody analiza difraktsionnykh dannykh i aktual'nye problemy rentgenovskoi optiki: 7-ya mezhdunarodnaya shkola-seminar molodykh uchenykh [Modern methods of analysis of diffraction data and actual problems of X-ray optics: the 7th international school-seminar of junior scientists]. 2020. 162 р.
  • Badrinarayanan V., Kendall A., Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence. 2017. V. 39. № 12. P. 2481–2495. https://doi.org/10.1109/TPAMI.2016.2644615
  • Benesty J., Chen J., Huang Y., Cohen I. Noise reduction in speech processing. Berlin, Heidelberg. Springer, 2009. V. 2. 230 p.
  • Borovikov P.I., Antonov E.N., Dunaev A.G., Krotova L.I., Sviridov A.P., Fatkhudinov T.Kh., Popov V.K. Model of the destruction of bioresorbable polymers in aqueous media. Inorg. Mater. Appl. Res. 2018. V. 9. P. 649–654. https://doi.org/10.1134/S2075113318040056
  • Brudfors M., Balbastre Y., Ashburner J., Rees G., Nachev P., Ourselin S., Cardoso M.J. An MRF-UNet Product of Experts for Image Segmentation. Proceedings of Machine Learning Research. 2021. arXiv preprint arXiv:2104.05495.
  • Buzug T.M. Computed tomography: From photon statistics to modern cone-beam CT. Springer Science &Business Media. Berlin. 2008. 522 p.
  • Chukalina M.V., Khafizov A.V., Kokhan V.V., Buzmakov A.V., Senin R.A., Uvarov V.I., Grigoriev M.V. Algorithm for post-processing of tomography images to calculate the dimension-geometric features of porous structures. Computer Optics. 2021. V. 45. № 1. P. 110–121. https://doi.org/10.18287/2412-6179-CO-781
  • Gonzalez R., Woods R. Digital Image Processing. Up-per Saddle River, Prentice Hall. 2002. 1192 p.
  • Gostick J.T., Khan Z.A., Tranter T.G., Kok M.D., Agnaou M., Sadeghi M., Jervis R. PoreSpy: A Python Toolkit for Quantitative Analysis of Porous Media Images. Journal of Open Source Software. 2019. V. 4. № 37. P. 1296–1299. https://doi.org/10.21105/joss.01296
  • Jaccard N., Szita N., Lewis D. G. Segmentation of phase contrast microscopy images based on multi-scale local Basic Image Features histograms. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2017. V. 5. № 5. P. 359–367. https://doi.org/10.1080/21681163.2015.1016243
  • Kurita T., Otsu N., Abdelmalek N. Maximum likelihood thresholding based onpopulation mixture models. Pattern Recognition. 1992. V. 25. № 10. P. 1231–1240. https://doi.org/10.1016/0031-3203(92)90024-D
  • Myttenaere A., Golden B., Le Grand B., Rossi F. Mean Absolute Percentage Error for regression models. Neurocomputing. 2016. V. 192. P. 38–48. https://doi.org/10.1016/j.neucom.2015.12.114
  • Ronneberger O., Fischer P., Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, LNCS. 2015. P. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
  • Shah S.M., Gray F., Crawshaw J.P., Boek E.S. Micro-computed tomography pore-scale study of flow in porous media: effect of voxel resolution. Advances in Water Resources. 2016. V. 95. P. 276–287. https://doi.org/10.1016/j.advwatres.2015.07.012
  • Shirani M.R., Safi-Esfahani F. Dynamic scheduling of tasks in cloud computing applying dragonfly algorithm, biogeography-based optimization algorithm and Mexican hat wavelet. The Journal of Supercomputing volume. 2021. V. 77. P. 1214–1272. https://doi.org/10.1007/s11227-020-03317-8
  • Uvarov V.I., Borovinskaya I.P., Lukin E.S., Tsodikov M.V., Golubev K.B. Catalytically active cermet membrane for converting byproducts from the production of combustibles. Glass Ceram. 2014. V. 71. P. 270–274. https://doi.org/10.1007/s10717-014-9667-1
  • Usanov M.S., Kulberg N.S., Morozov S.P. Experience of application of adaptive homophobic filters for computer tomograms processing. Journal of Information Technologies and Computing Systems. 2017. V. 2. P. 33–42.