• Acta Optica Sinica
  • Vol. 42, Issue 14, 1426001 (2022)
Xuelian Liu, Xudong Chen*, Zhili Lin**, Hui Liu, Xiangyu Zhu, and Xiaoxue Zhang
Author Affiliations
  • Key Laboratory of Optical Transmission and Transformation of Fujian Province, School of Information Science and Engineering, Huaqiao University, Xiamen 361021, Fujian , China
  • show less
    DOI: 10.3788/AOS202242.1426001 Cite this Article Set citation alerts
    Xuelian Liu, Xudong Chen, Zhili Lin, Hui Liu, Xiangyu Zhu, Xiaoxue Zhang. Deep-Learning-Assisted Detection For Topological Charges of Vortex Beams Through Strong Scattering Medium[J]. Acta Optica Sinica, 2022, 42(14): 1426001 Copy Citation Text show less
    Vortex phase distribution and amplitude distribution under different topological charges. (a)-(c) Vortex phase distribution;
    Fig. 1. Vortex phase distribution and amplitude distribution under different topological charges. (a)-(c) Vortex phase distribution;
    Speckles formed by vortex beam passing through strong and weak scattering media. (a)(d) Amplitude distribution patterns of vortex beam; (b)(e) speckle patterns after vortex beam passing through strong scattering medium; (c)(f) speckle patterns after vortex beam passing through weak scattering medium
    Fig. 2. Speckles formed by vortex beam passing through strong and weak scattering media. (a)(d) Amplitude distribution patterns of vortex beam; (b)(e) speckle patterns after vortex beam passing through strong scattering medium; (c)(f) speckle patterns after vortex beam passing through weak scattering medium
    Experimental optical path diagram of vortex beam passing through strong scattering medium
    Fig. 3. Experimental optical path diagram of vortex beam passing through strong scattering medium
    Speckle patterns formed by vortex beams with different topological charges passing through scattering medium
    Fig. 4. Speckle patterns formed by vortex beams with different topological charges passing through scattering medium
    Speckle pattern and local magnification of vortex beam with different topological charges. (a) l=1; (b) l=10
    Fig. 5. Speckle pattern and local magnification of vortex beam with different topological charges. (a) l=1; (b) l=10
    Neural network structure
    Fig. 6. Neural network structure
    Curves of training loss and validation loss in 10 epochs
    Fig. 7. Curves of training loss and validation loss in 10 epochs
    Curves of training accuracy and validation accuracy in 10 epochs
    Fig. 8. Curves of training accuracy and validation accuracy in 10 epochs
    Accuracy of prediction
    Fig. 9. Accuracy of prediction
    LayerNumber of input channelsNumber of output channelsKernel sizeStrideInputOutput
    Relu(Conv2d)132(5,5)(1,1)(1,256,256)(32,252,252)
    Maxpool2d3232(2,2)(2,2)(32,252,252)(32,126,126)
    Relu(Conv2d)3264(5,5)(1,1)(32,126,126)(64,122,122)
    Maxpool2d6464(2,2)(2,2)(64,122,122)(64,61,61)
    Linear64×61×6140962381444096
    Linear40965124096512
    Linear5122051220
    Table 1. Parameter setting of each layer of neural network
    Xuelian Liu, Xudong Chen, Zhili Lin, Hui Liu, Xiangyu Zhu, Xiaoxue Zhang. Deep-Learning-Assisted Detection For Topological Charges of Vortex Beams Through Strong Scattering Medium[J]. Acta Optica Sinica, 2022, 42(14): 1426001
    Download Citation