(48-6) 14 * << * >> * Русский * English * Содержание * Все выпуски

Applying neural networks in coordinated group signal transformation to improve image quality
E.A. Lopukhova 1, G.S. Voronkov 1, I.V. Kuznetsov 1, V.V. Ivanov 1, R.V. Kutluyarov 1, A.Kh. Sultanov 1, E.P. Grakhova 1

1 Ufa University of Science and Technology,
450076, Russian Federation, Ufa, Zaki Validi street 32

  PDF, 1866 kB

DOI: 10.18287/2412-6179-CO-1431

Страницы: 924-931.

Язык статьи: English.

Аннотация:
The rapid development of the Internet of Things and wireless sensor networks combined with the introduction of image analysis systems and computer vision technologies has led to the emergence of a new class of systems – multimedia Internet of Things and multimedia wireless sensing networks. The combination of the specifics of the Internet of Things, which requires simultaneous and long-term operation of a large number of autonomous devices, with the need to transmit video data poses the problem of creating new energy-efficient methods of image compression. The paper considers applying coordinated group signal transformation as such an algorithm, which performs compression based on the input signals’ correlation. Correlation between the image color channels makes this possible. However, it was necessary to supplement this method by clustering the original images using machine learning methods for better image reconstruction at reception. The criterion for clustering was the change of image gradient. The use of radial neural network in the clustering algorithm increased the speed of the proposed method. The resulting algorithm provides at least fourfold image compression with high-quality image restoration. Moreover, for multimedia Internet of Things systems, in which quality losses are acceptable, it is possible to provide large compression ratios without increasing computational complexity, i.e., without increasing power consumption.

Ключевые слова:
energy efficiency, image processing, machine learning.

Благодарности
The research was supported by Russian Science Foundation, agreement No. 21-79-10407 (mathematical model), by the Ministry of Science and Higher Education of the Russian Federation: state assignment for USATU, agreement No. 075-03-2021-014 dated 29.09.2021 (FEUE-2021-0013) (algorithm adaptation), and by the Ministry of Science and Higher Education of the Republic of Bashkortostan, agreement №1 dated 28.12.2021 (simulation and analisys).

Citation:
Lopukhova EA, Voronkov GS, Kuznetsov IV, Ivanov VV, Kutluyarov RV, Sultanov AKh, Grakhova EP. Applying neural networks in coordinated group signal transformation to improve image quality. Computer Optics 2024; 48(6): 924-931. DOI: 10.18287/2412-6179-CO-1431.

References:
  1. Amutha J, Sharma S, Nagar J. WSN strategies based on sensors, deployment, sensing models, coverage and energy efficiency: Review, approaches and open issues. Wirel Pers Commun 2020; 2(111): 1089-1115. DOI: 10.1007/s11277-019-06903-z.
  2. Nauman A, Qadri YA, Amjad M, Zikria YB, Afzal MK, Kim SW. Multimedia internet of things: A comprehensive survey. IEEE Access 2020; 8: 2100-2113. DOI: 10.1109/ACCESS.2020.2964280.
  3. Marlapalli K, Bandlamudi RSBP, Busi R, Pranav V, Madhavrao B. A review on image compression techniques. In Book: Satapathy SC, Bhateja V, Ramakrishna Murty M, Gia Nhu N, Kotti J, eds. Communication software and networks. Singapure: Springer Nature Singapore Pte Ltd; 2021: 271-279. DOI: 10.1007/978-981-15-5397-4_29.
  4. Rahman MA, Hamada M, Shin J. The impact of state-of-the-art techniques for lossless still image compression. Electronics 2021; 3(10): 360. DOI: 10.3390/electronics10030360.
  5. Ma S, Zhang X, Jia C, Zhao Z, Wang S, Wang S. Image and video compression with neural networks: A review. IEEE Trans Circuits Syst Video Technol 2020; 6(30): 1683-1698. DOI: 10.1109/TCSVT.2019.2910119.
  6. Uthayakumar J, Elhoseny M, Shankar K. Highly reliable and low-complexity image compression scheme using neighborhood correlation sequence algorithm in WSN. IEEE Trans Reliab 2020; 4(69): 1398-1423. DOI: 10.1109/TR.2020.2972567.
  7. Ma T, Hempel M, Peng D, Sharif H. A survey of energy-efficient compression and communication techniques for multimedia in resource constrained systems. IEEE Commun Surv Tutor 2013; 22: 963-972. DOI: 10.1109/SURV.2012.060912.00149.
  8. Ivanov VV, Abdreev IO, Lopukhova EA, Voronkov GS, Grakhova EP, Kuznetsov IV. Coordinated group codec for systems with highly correlated signals on the ESP32 microcontroller. 2023 IEEE Ural-Siberian Conf on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) 2023: 174-177. DOI: 10.1109/USBEREIT58508.2023.10158848.
  9. UC Berkeley Computer Vision Group – Contour detection and image segmentation – Resources. Source:              <https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html>.
  10. Leordeanu M, Sukthankar R, Sminchisescu C. Generalized boundaries from multiple image interpretations. IEEE Trans Pattern Anal Mach Intell 2014; 36(7): 1312-1324. DOI: 10.1109/TPAMI.2014.17.
  11. Premachandran V, Bonev B, Lian X, Yuille AL. PASCAL boundaries: A semantic boundary dataset with a deep semantic boundary detector. 2017 IEEE Winter Conf on Applications of Computer Vision (WACV) 2017: 73-81. DOI: 10.1109/WACV.2017.16.
  12. Wang B, He J, Yu L, Xia GS, Yang W. Event enhanced high-quality image recovery. In Book: Vedaldi A, Bischof H, Brox T, Frahm J-M, eds. Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIII. Cham: Springer Nature Switzerland AG; 2020: 155-171. DOI: 10.1007/978-3-030-58601-0_10.
  13. Sara U, Akter M, Uddin MS. Image quality assessment through FSIM, SSIM, MSE and PSNR – A comparative study. J Comput Commun 2019; 7(3): 8-18. DOI: 10.4236/JCC.2019.73002.
  14. Turgut SS, Oral M. Multi-focus image fusion based on gradient transform. arXiv Preprint. 2022. Source: <https://arxiv.org/abs/2204.09777>. DOI: 10.48550/arXiv.2204.09777.
  15. Cheng G, Liu L. Survey of image segmentation methods based on clustering. Proc 2020 IEEE Int Conf on Information Technology, Big Data and Artificial Intelligence (ICIBA) 2020: 1111-1115. DOI: 10.1109/ICIBA50161.2020.9277287.
  16. Duriez T, Brunton SL, Noack BR. Machine learning control (MLC). Fluid Mechanics and its Applications 2017; 116: 11-48. DOI: 10.1007/978-3-319-40624-42.
  17. Dash ChSK, Behera AK, Dehuri S, Cho SB. Radial basis function neural networks: A topical state-of-the-art survey. Open Comput Sci 2016; 1(6): 33-63. DOI: 10.1515/COMP-2016-0005.
  18. Turcza P, Duplaga M. Energy-efficient image compression algorithm for high-frame rate multi-view wireless capsule endoscopy. J Real-Time Image Pr 2019; 5(16): 1425-1437. DOI: 10.1007/s11554-016-0653-4.
  19. Alam MW, Sohag MdHAS, Khan AH, Sultana T, Wahid KA. IoT-Based intelligent capsule endoscopy system: A technical review. In Book: Hemanth DJ, Gupta D, Balas VE, eds. Intelligent data analysis for biomedical applications. Ch 1. Academic Press; 2019: 1-20. DOI: 10.1016/B978-0-12-815553-0.00001-X.
  20. Chen C-A, Chen S-L, Lioa C-H, Abu PAR. Lossless CFA image compression chip design for wireless capsule endoscopy. IEEE Access 2019; 7: 107047-107057. DOI: 10.1109/ACCESS.2019.2930818.
  21. Sheeja R, Sutha J. Soft fuzzy computing to medical image compression in wireless sensor network-based tele medicine system. Multimed Tools Appl 2020; 79: 10215-10232. DOI: 10.1109/ACCESS.2019.2930818.
  22. Ivanov VV, Lopukhova EA, Voronkov GS, Kuznetsov IV, Grakhova EP. Efficiency evaluation of group signals transformation for wireless communication in V2X systems. Proc 2022 Ural-Siberian Conf on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) 2022: 167-170. DOI: 10.1109/USBEREIT56278.2022.9923401.
  23. Xu J, Moussawi A, Gras R, Lubineau G. Using image gradients to improve robustness of digital image correlation to non-uniform illumination: effects of weighting and normalization choices. Exp Mech 2015; 55: 963-979. DOI: 10.1007/S11340-015-9996-1.
  24. Sun Z, Feng W, Zhao Q, Huang L. Brightness preserving image enhancement based on a gradient and intensity histogram. J Electron Imaging 2015; 24(5): 053006. DOI: 10.1117/1.JEI.24.5.053006.
  25. Jing G, Choi YK, Wang J, Wang W. Gradient guided image interpolation. 2014 IEEE Int Conf on Image Processing (ICIP) 2014: 1822-1826. DOI: 10.1109/ICIP.2014.7025365.

© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: journal@computeroptics.ru; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20