Abstract—Image capturing is often performed with distortions caused by inaccurate focusing, displacement of the scene or recorder, radiation dispersion in the signal transmission medium, and similar aberrations. The distortion operator, which is commonly unknown, is needed for image restoration. Therefore, the determination of type and parameters of distortions using the observed signal is actual. In the paper a new approach to distortions diagnostics of video information by means of deep neural networks is proposed. The task of determination of the type and parameters of the main linear homogeneous distortion operators (circular with rectangular profile, circular with Gaussian profile, and linear with rectangular profile) is considered. An application of neural networks with the ResNet50, ResNet29, and ResNet18 architectures to identify the type and to determine the distortions parameters is studied. The research shows that the efficiency of the neural network is no less than that of methods based on direct spectral analysis.
Similar content being viewed by others
REFERENCES
S. Tiwari, V. P. Shukla, and A. K. Singh, “Review of motion blur estimation techniques,” J. Image & Graph. 1 (4), 176–184 (2013).
R. Dash and B. Majhi, “Motion blur parameters estimation for image restoration,” Optik 125, 1634–1640 (2014).
Y. X. Song and Y. M. Zhang, “Parameter estimation and restoration of motion blurred image,” Appl. Mech. Mater. 608–609, 855–859 (2014).
J. P. A. Oliveira, M. A. T. Figueiredo, and J. M. Bioucas-Dias, “Blind estimation of motion blur parameters for image deconvolution,” in Proc. 3rd Iberian Conf. (IbPRIA), Girona, Spain, June 6–8, 2007 (IbPRIA, 2007), Vol. 4478, pp. 604–611.
M. Liang, “Parameter estimation for defocus blurred image based on polar transformation,” Rev. Tec. Ing. Univ. Zulia 39 (1), 333–338 (2016).
X. Zhu, S. Cohen, S. Schiller, and P. Milanfar, “Estimating spatially varying defocus blur from a single image,” IEEE Trans. Image Process. 22, 4879–4891 (2013).
R. Gajjar, A. Pathak, and T. Zaveri, “Defocus blur parameter estimation technique,” Int. J. Electron. Commun. Eng. & Technol. (IJECET) 7 (4), 85–90 (2016).
O. P. Milukova and P. A. Chochia, “Application of metrical and topological image characteristics for distortion diagnostics in the signal restoration problem,” J. Commun. Technol. Electron. 63, 637–642 (2018).
P. A. Chochia, “Diagnostics of a linear homogeneous distorting operator on the observed image spectrum,” J. Commun. Technol. Electron. 65, 725–734 (2020).
W. Pratt, Digital Image Processing (Wiley, New York, 1978; Mir, Moscow, 1982).
R. C. Gonzalez, and R. E. Woods, Digital Image Processing (Prentice Hall, Upper Saddle River, New Jersey, 2008).
S. J. Reeves, Image Restoration: Fundamentals of Image Restoration, in Academic Press Library in Signal Processing, ed. S. Theodoridis and R. Chellappa, Vol. 4, Pt. 6: Image, Video Processing and Analysis, Hardware, Audio, Acoustic and Speech Processing (Elsevier, 2014), pp. 164–192.
M. Cannon, “Blind deconvolution of spatially invariant image blurs with phase,” IEEE Trans. Acoust., Speech, Signal Process. 24, 58–63 (1976).
K. He, X. Zhang, Sh. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Stanford, CA, (2016), pp. 770–778.
G. Huang, Z. Liu, K. Q. Weinberger, and L. Van der Maaten, “Densely connected convolutional networks,” in IEEE Proc. Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, (2017), pp. 2261–2269.
A. Gully and F. Pal, Deep Learning with Keras (Packt Publihing, Moscow, 2017; DMK Press, Moscow, 2018).
D. P. Kingma and J. Ba. Adam, “A method for stochastic optimization,” in Proc. 3rd Int. Conf. on Learning Representations (ICLR), San Diego: CA, 2015, pp. 1–15. (arXiv preprint arXiv:1412.6980)
Author information
Authors and Affiliations
Corresponding authors
Additional information
Translated by A. Chikishev
Rights and permissions
About this article
Cite this article
Solomentsev, I.K., Chochia, P.A. Application of Neural Networks to Diagnose the Type and Parameters of Image Distortions. J. Commun. Technol. Electron. 65, 1499–1504 (2020). https://doi.org/10.1134/S1064226920120165
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064226920120165