• Spectroscopy and Spectral Analysis
  • Vol. 42, Issue 10, 3298 (2022)
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
    DOI: 10.3964/j.issn.1000-0593(2022)10-3298-09 Cite this Article
    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 Copy Citation Text show less
    Feature selection
    Fig. 1. Feature selection
    The establishment process of the shellfish image dataset
    Fig. 2. The establishment process of the shellfish image dataset
    Images of part of the shellfish dataset
    Fig. 3. Images of part of the shellfish dataset
    Some images of shellfish with high similarity
    Fig. 4. Some images of shellfish with high similarity
    Bar chart of sample distribution
    Fig. 5. Bar chart of sample distribution
    Training results of Resnest neural network model
    Fig. 6. Training results of Resnest neural network model
    Comparison of training results of four network models
    Fig. 7. Comparison of training results of four network models
    Comparison of training results of three network models
    Fig. 8. Comparison of training results of three 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 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/%
    SN_Net[9]25 50089.04
    MutualNet[12]24 78092.53
    FL_Net(本文)22 32093.38
    Table 2. Comparison of test results of four network models
    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