New sustainable methods for distorted image recovering
https://doi.org/10.17586/0021-3454-2023-66-7-559-567
Abstract
New sustainable methods and algorithms are proposed for recovering object images damaged (distorted, corrupted) as a result of defocusing, spreading, and noising. The type and parameters of damage are estimated by the developed “spectral method”, as demonstrated on the example of distorted images of the Black Sea, and then the image damage is eliminated (removed) based on a stable solution of integral equations using the Tikhonov regularization method and the Fourier transform. The approach makes it possible to increase the resolution of optical instruments - cameras, telescopes, microscopes, etc.
Keywords
defocusing,
spreading,
noising,
integral equations,
“spectral method” for damage type and parameters estimating,
elimination (removal),
resection (damage),
MatLab
Supporting agencies: the work was carried out within the framework of research project No. 620164 "Artificial intelligence methods for cyber-physical systems".
About the Authors
V. S. Sizikov
ITMO University
Russian Federation
Russian Federation
Valery S. Sizikov - Dr. Sci., Professor; Faculty of Software Engineering and Computer Technique
N. G. Rushchenko
ITMO University
Russian Federation
Russian Federation
Nina G. Rushchenko - PhD, Associate Professor; Faculty of Software Engineering and Computer Technique
References
1. Gonzalez R.C., Woods R.E. Digital Image Processing, New Jersey, Prentice Hall, 2002, 793 p.
2. Sizikov V.S. J. Optical Technology, 2017, no. 2(84), pp. 95–101, DOI: 10.1364/JOT.84.000095.
3. Sizikov V. et al. Computers, 2020, no. 30(9), pp. 1–16, DOI: 10.3390/computers9020030.
4. Voskoboinikov Yu.E. and Litasov V.A. Avtometriya (Optoel. Instrum. Data Proces.), 2006, no. 6(42), pp. 3–15.
5. Boikov I.B., Kravchenko M.V., Kryuchko V.I. Izvestiya RAS, Physics of the Solid Earth, 2010, no. 4(16), pp. 339–349.
6. Gruzman I.S., Kirichuk V.S., Kosykh V.P., Peretyagin G.I., Spektor A.A. Tsifrovaya obrabotka izobrazheniy v informatsionnykh sistemakh (Digital Image Processing in Information Systems), Novosibirsk, 2002, 352 р. (in Russ.)
7. Sizikov V.S. Pryamyye i obratnyye zadachi vosstanovleniya izobrazheniy, spektroskopii i tomografii s MatLab (Direct and Inverse Problems of Image Reconstruction, Spectroscopy and Tomography with MatLab), St. Petersburg, 2017, 412 р. (in Russ.)
8. Sizikov V.S., Dovgan A.N., Tsepeleva A.D. J. Optical Technology, 2020, no. 2(87), pp. 110–116, DOI: 10.1364/JOT.87.000110.
9. Sizikov V., Loseva P., Medvedev E., Sharifullin D., Dovgan A., Rushchenko N. CEUR Workshop Proc., 2020, no. 11(2893).
10. Gonsales R.C., Woods R.E., Eddins S.L. Digital Image Processing using MATLAB, New Jersey, Prentice Hall, 2004, 609 p.
11. Hansen P.C. Discrete Inverse Problems: Insight and Algorithms, Philadelphia, SIAM, 2010, 213 p.
12. Fergus R. et al. ACM Trans. Graphics, 2006, no. 3(25), pp. 787–794.
13. Cho S., Lee S. ACM Trans. Graphics, 2009, no. 5(28), art. no. 145, DOI: 10.1145/1618452.1618491.
14. Sizikov V.S. Obratnyye prikladnyye zadachi i MatLab (Inverse Applications and MatLab), St. Petersburg, 2011, 256 р. (in Russ.)
15. Petrov Yu.P., Sizikov V.S. Well-Posed, Ill-Posed, and Intermediate Problems with Applications, Leiden–Boston, VSP, 2005, 234 pp.
16. Kabanikhin S.I. Inverse and Ill-posed Problems: Theory and Applications, Berlin, Walter de Gruyter, 2011, 459 p.
17. Pronina V.S. Vosstanovleniye izobrazheniy s pomoshch'yu obuchayemykh optimizatsionno-neyrosetevykh algoritmov (Image Restoration Using Trainable Optimization Neural Network Algorithms), Extended abstract of candidate’s thesis, Moscow, 2023, 36 р. (in Russ.)
18. Sidorov D. Integral Dynamical Models: Singularities, Signals and Control, Singapore–London, World Sci. Publ., 2014, 343 p.
19. Protasov K.T., Belov V.V., Molchunov N.V. Optics Atmos. Ocean., 2000, no. 2(13), pp. 139–145.
20. Voskoboinikov Yu.E. Optoel. Instrum. Data Proces., 2007, no. 6(43), pp. 489–499, DOI: 10.3103/S8756699007060015.
21. Antonova T.V. Siberian J. Numer. Mathem., 2015, no. 2(18), pp. 107–120, DOI: 10.15372/SJNM20150201.
22. Solodusha S.V. Metody postroyeniya integral'nykh modeley dinamicheskikh sistem: algoritmy i prilozheniya v energetike (Methods for Constructing Integral Models of Dynamic Systems: Algorithms and Applications in the Power Industry), Extended abstract of Doctor’s thesis, Irkutsk, 2019, 44 р. (in Russ.)
23. Egoshkin N.A., Eremeev V.V. Digital signal processing, 2010, no. 4, pp. 28–32. (in Russ.)
24. Sizikov V.S. Intern. J. Artific. Intelligence, 2015, no. 1(13), pp. 184–199.
25. Sizikov V.S., Dovgan' A.N., Lavrov A.V. Ustoychivyye metody matematiko-komp'yuternoy obrabotki izobrazheniy i spektry (Stable Methods of Mathematical-Computer Processing of Images and Spectra), St. Petersburg, 2022, 70 р. (in Russ.)
Review
For citations:
Sizikov V.S., Rushchenko N.G. New sustainable methods for distorted image recovering. Journal of Instrument Engineering. 2023;66(7):559-567. (In Russ.) https://doi.org/10.17586/0021-3454-2023-66-7-559-567
Views:
29
Email this article 