EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Neural Network for Holographic Reconstruction of Pseudorandom Binary Data

Mikhail K. Drozdov, Dmitry A. Rymov, Andrey S. Svistunov, Pavel A. Cheremkhin, Anna V. Shifrina, Semen A. Kiriy, Evgenii Yu. Zlokazov, Elizaveta K. Petrova, Vsevolod A. Nebavskiy, Nikolay N. Evtikhiev, Rostislav S. Starikov

Technologies · 19.10.2025 · 13 (10) · 474

DOI: 10.3390/technologies13100474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 19.10.2025. Verfasst von Mikhail K. Drozdov und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural networks are a state-of-the-art technology for fast and accurate holographic image reconstruction. However, at present, neural network-based reconstruction methods are predominantly applied to objects with simple, homogeneous spatial structures: blood cells, bacteria, microparticles in solutions, etc. However, in the case of objects with high contrast details, the reconstruction needs to be as precise as possible to successfully extract details and parameters. In this paper we investigate the use of neural networks in holographic reconstruction of spatially inhomogeneous binary data containers (QR codes). Two modified lightweight convolutional neural networks (which we named HoloLightNet and HoloLightNet-Mini) with an encoder–decoder architecture have been used for image reconstruction. These neural networks enable high-quality reconstruction, guaranteeing the successful decoding of QR codes (both in demonstrated numerical and optical experiments). In addition, they perform reconstruction two orders of magnitude faster than more traditional architectures. In optical experiments with a liquid crystal spatial light modulator, the obtained bit error rate was equal to only 1.2%. These methods can be used for practical applications such as high-density data transmission in coherent systems, development of reliable digital information storage and memory techniques, secure optical information encryption and retrieval, and real-time precise reconstruction of complex objects.

Förderung

  • Russian Science Foundation

Zitieren

APA

Drozdov, M. K., Rymov, D. A., Svistunov, A. S., Cheremkhin, P. A., Shifrina, A. V., Kiriy, S. A., Zlokazov, E. Y., Petrova, E. K., Nebavskiy, V. A., Evtikhiev, N. N., & Starikov, R. S. (2025). Lightweight Neural Network for Holographic Reconstruction of Pseudorandom Binary Data. Technologies, 13(10), 474. https://doi.org/10.3390/technologies13100474

Vancouver

Drozdov MK, Rymov DA, Svistunov AS, Cheremkhin PA, Shifrina AV, Kiriy SA, et al. Lightweight Neural Network for Holographic Reconstruction of Pseudorandom Binary Data. Technologies. 2025;13(10):474. doi:10.3390/technologies13100474

BibTeX
@article{Drozdov2025,
  author = {Drozdov, Mikhail K. and Rymov, Dmitry A. and Svistunov, Andrey S. and Cheremkhin, Pavel A. and Shifrina, Anna V. and Kiriy, Semen A. and Zlokazov, Evgenii Yu. and Petrova, Elizaveta K. and Nebavskiy, Vsevolod A. and Evtikhiev, Nikolay N. and Starikov, Rostislav S.},
  title = {Lightweight Neural Network for Holographic Reconstruction of Pseudorandom Binary Data},
  journal = {Technologies},
  year = {2025},
  volume = {13},
  number = {10},
  pages = {474},
  doi = {10.3390/technologies13100474}
}
Kostenlos starten →