Spectroscopy and Spectral Analysis, Volume. 42, Issue 10, 3298(2022)

Recognition of Shellfish Based on Visible Spectrum and Convolutional Neural Network

Yang ZHANG1、1; 2;, Jun YUE1、1; *;, Shi-xiang JIA1、1;, Zhen-bo LI2、2;, and Guo-rui SHENG1、1;
Author Affiliations
  • 11. School of Information and Electrical Engineering, Ludong University, Yantai 264025, China
  • 22. School of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China
  • show less
    Figures & Tables(10)
    Feature selection
    The establishment process of the shellfish image dataset
    Images of part of the shellfish dataset
    Some images of shellfish with high similarity
    Bar chart of sample distribution
    Training results of Resnest neural network model
    Comparison of training results of four network models
    Comparison of training results of three network models
    • Table 1. Comparison of test results of four network models

      View table
      View in Article

      Table 1. Comparison of test results of four network models

      网络模型训练时长/s测试集平均正确率/%
      Resnest23 28092.20
      F_Net25 08093.13
      L_Net22 26092.57
      FL_Net22 32093.38
    • Table 2. Comparison of test results of four network models

      View table
      View in Article

      Table 2. Comparison of test results of four network models

      网络模型训练时长/s测试集平均正确率/%
      SN_Net[9]25 50089.04
      MutualNet[12]24 78092.53
      FL_Net(本文)22 32093.38
    Tools

    Get Citation

    Copy Citation Text

    Yang ZHANG, Jun YUE, Shi-xiang JIA, Zhen-bo LI, Guo-rui SHENG. Recognition of Shellfish Based on Visible Spectrum and Convolutional Neural Network[J]. Spectroscopy and Spectral Analysis, 2022, 42(10): 3298

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: May. 26, 2021

    Accepted: Apr. 7, 2022

    Published Online: Nov. 23, 2022

    The Author Email:

    DOI:10.3964/j.issn.1000-0593(2022)10-3298-09

    Topics