| Peer-Reviewed

Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network

Received: 5 August 2023     Accepted: 28 August 2023     Published: 14 September 2023
Views:       Downloads:
Abstract

In the existing electronic communication systems, fast transmission of three-dimensional image information requires compression and encoding of holographic images. In this paper, a method for compressing the color computer-generated hologram by the quantum-inspired neural network based on the gradient optimized algorithm is proposed. By optimizing the gradient descent calculation method of quantum-inspired neural network, the convergence speed of the quantum-inspired neural network was improved, and the loss error of the quantum-inspired neural network was reduced. The bandwidth-limited angular spectrum method was used to calculate the color double-phase computer-generated hologram. Gradient optimized quantum-inspired neural networks and traditional quantum-inspired neural networks are used to compress the color double-phase computer-generated hologram respectively, and the decompressed color double-phase computer-generated hologram is reconstructed to the original color image by the angular spectrum method. It is shown that gradient-optimized quantum-inspired neural networks have better results in compressing and reconstructing color computer-generated holograms, which obtain high-quality and low color difference reconstructed original images compared to traditional quantum-inspired neural networks. Different gradient optimization algorithms also have differences in the training of computer-generated holograms at different wavelengths. Therefore, suitable gradient-optimized quantum-inspired neural networks can accelerate the compression speed of computer-generated holograms, while improving the quality of decompressed computer-generated holograms and reconstructed original images.

Published in American Journal of Optics and Photonics (Volume 11, Issue 1)
DOI 10.11648/j.ajop.20231101.11
Page(s) 1-9
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Computer Holography, Image Compression, Neural Network, Quantum Computing, Image Reconstruction

References
[1] M. Liu, G. Yang, and H. Xie, "Method of computer-generated hologram compression and transmission using quantum back-propagation neural network," Opt. Eng. 56(2), 023104 (2017).
[2] C. Zhang, G. Yang, and H. Xie, "Information compression of computer-generated hologram using BP neural network," in Biomedical Optics and 3-D Imaging, OSA Technical Digest (2010), paper JMA2.
[3] Y. Sun, G. Yang, and H. Xie, "Computer-generated hologram fast transmission using compressive sensing," in 2016 Imaging and Applied Optics, OSA Technical Digest (2016), paper JW4A.
[4] S. K. Jeswal and S. Chakraverty, "Recent Developments and Applications in Quantum Neural Network: A Review," Arch. Comput. Methods Eng. 26(4), 793–807 (2019).
[5] Z. A. Jia, B. Yi, R. Zhai, Y. C. Wu, G. C. Guo, and G. P. Guo, "Quantum Neural Network States: A Brief Review of Methods and Applications," Adv. Quantum Technol. 2(7–8), 1–16 (2019).
[6] D. Konar, S. Bhattacharyya, T. K. Gandhi, and B. K. Panigrahi, "A Quantum-Inspired Self-Supervised Network model for automatic segmentation of brain MR images," Appl. Soft Comput. J. 93, 106348 (2020).
[7] K. Mori, T. Isokawa, N. Kouda, N. Matsui, and H. Nishimura, "Qubit inspired neural network towards its practical applications," in the 2006 IEEE International Joint Conference on Neural Network Proceedings (2006), pp. 224-229.
[8] L. S. Panchi, "Learning algorithm and application of quantum BP neural networks based on universal quantum gates," J. Syst. Eng. Electron. 19(1), 167-174 (2008).
[9] C. Wang and J. H. Du, "Research of Image Compression Based on Quantum BP," Dianzi Yu Xinxi Xuebao/Journal Electron. Inf. Technol. 28(5), 848–851 (2006).
[10] M. Cao, "Quantum-inspired Neural Networks with Applications," Int. J. Comput. Inf. Technol. 03(01), 83–92 (2014).
[11] X. F. Niu and W. P. Ma, "Design of a novel quantum neural network," Laser Phys. Lett. 17(10), (2020).
[12] S. Hou, G. Yang, and H. Xie, "Optimized initial weight in quantum-inspired neural network for compressing computer-generated holograms," Opt. Eng. 58(05), 053105 (2019).
[13] K. Matsushima and T. Shimobaba, "Band-limited angular spectrum method for numerical simulation of free-space propagation in far and near fields," Opt. Express 17(22), 19662-19673 (2009).
[14] Y. K. Kim, J. S. Lee, and Y. H. Won, "Low-noise high-efficiency double-phase hologram by multiplying a weight factor," Opt. Lett. 44(15), 3649-3652 (2019).
[15] V. Arrizón and D. Sánchez-de-la-Llave, "Double-phase holograms implemented with phase-only spatial light modulators: performance evaluation and improvement," Appl. Opt. 41(17), 3436 (2002).
[16] S. Ruder, "An overview of gradient descent optimization algorithms," arXiv.1609.04747 (2016).
[17] D. K. R. Gaddam, M. D. Ansari, S. Vuppala, V. K. Gunjan, and M. M. Sati, "A Performance Comparison of Optimization Algorithms on a Generated Dataset," Lect. Notes Electr. Eng. 783 (January), 1407–1415 (2022).
[18] T. Shimobaba, M. Makowski, Y. Nagahama, Y. Endo, R. Hirayama, D. Hiyama, S. Hasegawa, M. Sano, T. Kakue, M. Oikawa, T. Sugie, N. Takada, and T. Ito, "Color computer-generated hologram generation using the random phase-free method and color space conversion," Appl. Opt. 55 (15), 4159-4165 (2016).
[19] T. Shimobaba, T. Kakue, and M. Oikawa, et al. "Calculation reduction method for color digital holography and computer-generated hologram using color space conversion," Opt. Eng. 53(2) 024108 (2014).
[20] H. Nakayama, N. Takada, Y. Ichihashi, S. Awazu, T. Shimobaba, N. Masuda, and T. Ito, "Real-time color electroholography using multiple graphics processing units and multiple high-definition liquid-crystal display panels," Appl. Opt. 49(31), 5993–5996 (2010).
[21] E. C. Larson and D. M. Chandler, "Most Apparent Distortion: A Dual Strategy for Full-Reference Image Quality Assessment," Image Qual. Syst. Perform. VI, 7242 (2009), paper 72420S.
Cite This Article
  • APA Style

    Jingyuan Ma, Guanglin Yang, Haiyan Xie. (2023). Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network. American Journal of Optics and Photonics, 11(1), 1-9. https://doi.org/10.11648/j.ajop.20231101.11

    Copy | Download

    ACS Style

    Jingyuan Ma; Guanglin Yang; Haiyan Xie. Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network. Am. J. Opt. Photonics 2023, 11(1), 1-9. doi: 10.11648/j.ajop.20231101.11

    Copy | Download

    AMA Style

    Jingyuan Ma, Guanglin Yang, Haiyan Xie. Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network. Am J Opt Photonics. 2023;11(1):1-9. doi: 10.11648/j.ajop.20231101.11

    Copy | Download

  • @article{10.11648/j.ajop.20231101.11,
      author = {Jingyuan Ma and Guanglin Yang and Haiyan Xie},
      title = {Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network},
      journal = {American Journal of Optics and Photonics},
      volume = {11},
      number = {1},
      pages = {1-9},
      doi = {10.11648/j.ajop.20231101.11},
      url = {https://doi.org/10.11648/j.ajop.20231101.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajop.20231101.11},
      abstract = {In the existing electronic communication systems, fast transmission of three-dimensional image information requires compression and encoding of holographic images. In this paper, a method for compressing the color computer-generated hologram by the quantum-inspired neural network based on the gradient optimized algorithm is proposed. By optimizing the gradient descent calculation method of quantum-inspired neural network, the convergence speed of the quantum-inspired neural network was improved, and the loss error of the quantum-inspired neural network was reduced. The bandwidth-limited angular spectrum method was used to calculate the color double-phase computer-generated hologram. Gradient optimized quantum-inspired neural networks and traditional quantum-inspired neural networks are used to compress the color double-phase computer-generated hologram respectively, and the decompressed color double-phase computer-generated hologram is reconstructed to the original color image by the angular spectrum method. It is shown that gradient-optimized quantum-inspired neural networks have better results in compressing and reconstructing color computer-generated holograms, which obtain high-quality and low color difference reconstructed original images compared to traditional quantum-inspired neural networks. Different gradient optimization algorithms also have differences in the training of computer-generated holograms at different wavelengths. Therefore, suitable gradient-optimized quantum-inspired neural networks can accelerate the compression speed of computer-generated holograms, while improving the quality of decompressed computer-generated holograms and reconstructed original images.},
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Compressing Color Computer-Generated Hologram Using Gradient Optimized Quantum-Inspired Neural Network
    AU  - Jingyuan Ma
    AU  - Guanglin Yang
    AU  - Haiyan Xie
    Y1  - 2023/09/14
    PY  - 2023
    N1  - https://doi.org/10.11648/j.ajop.20231101.11
    DO  - 10.11648/j.ajop.20231101.11
    T2  - American Journal of Optics and Photonics
    JF  - American Journal of Optics and Photonics
    JO  - American Journal of Optics and Photonics
    SP  - 1
    EP  - 9
    PB  - Science Publishing Group
    SN  - 2330-8494
    UR  - https://doi.org/10.11648/j.ajop.20231101.11
    AB  - In the existing electronic communication systems, fast transmission of three-dimensional image information requires compression and encoding of holographic images. In this paper, a method for compressing the color computer-generated hologram by the quantum-inspired neural network based on the gradient optimized algorithm is proposed. By optimizing the gradient descent calculation method of quantum-inspired neural network, the convergence speed of the quantum-inspired neural network was improved, and the loss error of the quantum-inspired neural network was reduced. The bandwidth-limited angular spectrum method was used to calculate the color double-phase computer-generated hologram. Gradient optimized quantum-inspired neural networks and traditional quantum-inspired neural networks are used to compress the color double-phase computer-generated hologram respectively, and the decompressed color double-phase computer-generated hologram is reconstructed to the original color image by the angular spectrum method. It is shown that gradient-optimized quantum-inspired neural networks have better results in compressing and reconstructing color computer-generated holograms, which obtain high-quality and low color difference reconstructed original images compared to traditional quantum-inspired neural networks. Different gradient optimization algorithms also have differences in the training of computer-generated holograms at different wavelengths. Therefore, suitable gradient-optimized quantum-inspired neural networks can accelerate the compression speed of computer-generated holograms, while improving the quality of decompressed computer-generated holograms and reconstructed original images.
    VL  - 11
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Laboratory of Signal and Information Processing, School of Electronics, Peking University, Beijing, China

  • Laboratory of Signal and Information Processing, School of Electronics, Peking University, Beijing, China

  • China Science Patent and Trademark Agent, Beijing, China

  • Sections