Image Reconstruction of Multimode Fiber Scattering Media Based on Deep Learning

被引:0
|
作者
Meng L. [1 ]
Hu H. [1 ,2 ]
Hu J. [1 ]
Bu S. [1 ]
Gao H. [1 ]
机构
[1] College of Information Science and Engineering, Northeastern University, Shenyang
[2] School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai
来源
Meng, Lu (menglu@ise.neu.edu.cn) | 1600年 / Science Press卷 / 47期
关键词
Deep learning; Dense connection; DenseUnet; Fiber optics; Image processing; Image reconstruction; Multimode fiber;
D O I
10.3788/CJL202047.1206005
中图分类号
学科分类号
摘要
Multimode fiber is a thick scattering medium. When the target image is projected onto the multimode optical fiber, multimode coupling will occur, thereby generating speckle images at the output of the fiber. In this work, multimode optical fiber imaging is restored based on deep learning, and the distortion of thick scattering media imaging is solved. DenseUnet is used and the speckle image is used as the input of the model for reconstructing the target image. The DenseUnet model employs a fusion mechanism to deepen the network depth, thus, improving the reconstruction accuracy and realizing good robustness. The experimental results reveal that DenseUnet can be used to reconstruct speckle images produced by multimode optical fibers with different lengths. © 2020, Chinese Lasers Press. All right reserved.
引用
收藏
相关论文
共 21 条
  • [1] Li S, Deng M, Lee J, Et al., Imaging through glass diffusers using densely connected convolutional networks, Optica, 5, 7, pp. 803-813, (2018)
  • [2] Rahmani B, Loterie D, Konstantinou G, Et al., Multimode optical fiber transmission with a deep learning network, Light: Science & Applications, 7, (2018)
  • [3] Fan P F, Zhao T R, Su L., Deep learning the high variability and randomness inside multimode fibres
  • [4] Wang P, Di J L., Deep learning-based object classification through multimode fiber via a CNN-architecture SpeckleNet, Applied Optics, 57, 28, pp. 8258-8263, (2018)
  • [5] Lu H M, Li Y J, Uemura T, Et al., Low illumination underwater light field images reconstruction using deep convolutional neural networks, Future Generation Computer Systems, 82, pp. 142-148, (2018)
  • [6] Zhao J, Sun Y Y, Zhu H B, Et al., Deep-learning cell imaging through Anderson localizing optical fiber, Advanced Photonics, 1, 6, (2019)
  • [7] Vellekoop I M, Mosk A P., Focusing coherent light through opaque strongly scattering media, Optics Letters, 32, 16, pp. 2309-2311, (2007)
  • [8] Huang H L, Chen Z Y, Sun C Z, Et al., Focusing laser beams through opaque scattering media, Chinese Journal of Lasers, 42, 6, (2015)
  • [9] Yaqoob Z, Psaltis D, Feld M S, Et al., Optical phase conjugation for turbidity suppression in biological samples, Nature Photonics, 2, 2, pp. 110-115, (2008)
  • [10] Li C M Y., Optical phase conjugation (OPC) for focusing light through/inside biological tissue, Infrared and Laser Engineering, 48, 7, (2019)