Spectroscopy and Spectral Analysis, Volume. 41, Issue 11, 3552(2021)

Classification of Impurities in Machine-Harvested Seed Cotton Using Hyperspectral Imaging

Jin-qiang CHANG*, Ruo-yu ZHANG*;, Yu-jie PANG, Meng-yun ZHANG, and Ya ZHA
Author Affiliations
  • College of Mechanical and Electrical Engineering, Shihezi University/Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture, Shihezi 832003, China
  • show less
    Figures & Tables(11)
    Machine-harvested seed cotton and main impurities
    Hyperspectral imaging system1: CCD camera; 2: Spectrograph; 3: Lens; 4: Halogen lamps ;5: Sample; 6: Stage; 7: Controller; 8: Computer
    Mean spectra of mechine-harvested cotton and impurities
    Eigenvalues and cumulative contribution rates of the first 6 principal components
    Scatter clusters of the first 2 principal components
    Scattering clusters of the first 2 variables of LDA(a): All 6 types of materials; (b): Leaf, bell shell inner, stem
    Parameter optimization results of SVM model
    Parameter optimization results of ANN model
    Pie chart of prediction
    Hyperspectral image classification results in pixel level(a): Original image; (b): Classification result
    • Table 1. Accuracy and runtime of three classification models

      View table
      View in Article

      Table 1. Accuracy and runtime of three classification models

      算法训练集/%测试集/%全部数据/%检测用时/s
      LDA86.486.286.31.86
      SVM83.483.483.473.65
      ANN82.981.882.62.58
    Tools

    Get Citation

    Copy Citation Text

    Jin-qiang CHANG, Ruo-yu ZHANG, Yu-jie PANG, Meng-yun ZHANG, Ya ZHA. Classification of Impurities in Machine-Harvested Seed Cotton Using Hyperspectral Imaging[J]. Spectroscopy and Spectral Analysis, 2021, 41(11): 3552

    Download Citation

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

    Category: Orginal Article

    Received: Aug. 28, 2020

    Accepted: --

    Published Online: Dec. 17, 2021

    The Author Email: Jin-qiang CHANG (changjinq@163.com)

    DOI:10.3964/j.issn.1000-0593(2021)11-3552-07

    Topics