• Spectroscopy and Spectral Analysis
  • Vol. 42, Issue 10, 3291 (2022)
Fu ZHANG1、1; 2; 3;, Xin-yue WANG2、2;, Xia-hua CUI2、2;, Wei-hua CAO2、2;, Xiao-dong ZHANG1、1; *;, and Ya-kun ZHANG2、2;
Author Affiliations
  • 11. Key Laboratory of Modern Agricultural Equipment and Technology of Ministry of Education, Jiangsu University, Zhenjiang 212013, China
  • 22. College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang 471003, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2022)10-3291-07 Cite this Article
    Fu ZHANG, Xin-yue WANG, Xia-hua CUI, Wei-hua CAO, Xiao-dong ZHANG, Ya-kun ZHANG. Classification of Qianxi Tomatoes by Visible/Near Infrared Spectroscopy Combined With GMO-SVM[J]. Spectroscopy and Spectral Analysis, 2022, 42(10): 3291 Copy Citation Text show less
    Qianxi samples(a): Type 1; (b): Type 2; (c): Type 3; (d): Type 4
    Fig. 1. Qianxi samples
    (a): Type 1; (b): Type 2; (c): Type 3; (d): Type 4
    Spectral acquisition system①: Spectrometer; ②: Light source; ③: Y type fiber; ④: Computer
    Fig. 2. Spectral acquisition system
    ①: Spectrometer; ②: Light source; ③: Y type fiber; ④: Computer
    Schematic diagram of acquisition location
    Fig. 3. Schematic diagram of acquisition location
    Average reflectivity curves of Qianxi tomato samples
    Fig. 4. Average reflectivity curves of Qianxi tomato samples
    Spectral average reflectivity curves after preprocessing
    Fig. 5. Spectral average reflectivity curves after preprocessing
    Characteristic wavelengths extracted by successive projections algorithm(a): Number of characteristic wavelengths;(b): Corresponding characteristic wavelength
    Fig. 6. Characteristic wavelengths extracted by successive projections algorithm
    (a): Number of characteristic wavelengths;(b): Corresponding characteristic wavelength
    Classification results of training set
    Fig. 7. Classification results of training set
    Classification results of test set
    Fig. 8. Classification results of test set
    Training set classification results
    Fig. 9. Training set classification results
    Classification results of test set
    Fig. 10. Classification results of test set
    Accuracy comparison of training set
    Fig. 11. Accuracy comparison of training set
    Accuracy comparison of test set
    Fig. 12. Accuracy comparison of test set
    数据集训练集测试集总计
    类别1402060
    类别2402060
    类别3402060
    类别4402060
    总计16080240
    Table 1. Sample partition results
    样本类别样本数目预测正确数目准确率/%
    类别1403485.0
    类别2402050.0
    类别3402665.0
    类别4401537.5
    Table 2. Classification results of training set
    样本类别样本数目预测正确数目准确率/%
    类别1201785
    类别220945
    类别320840
    类别420525
    Table 3. Classification results of test set
    参数训练集
    c56.888 3
    g36.971 1
    Table 4. Optimized SVM parameters
    样本类别样本数目预测正确数目准确率/%
    类别14040100
    类别24040100
    类别34040100
    类别44040100
    Table 5. Classification results of training set
    样本类别样本数目预测正确数目准确率/%
    类别1201995
    类别2201785
    类别3201260
    类别4201785
    Table 6. Classification results of test set
    Fu ZHANG, Xin-yue WANG, Xia-hua CUI, Wei-hua CAO, Xiao-dong ZHANG, Ya-kun ZHANG. Classification of Qianxi Tomatoes by Visible/Near Infrared Spectroscopy Combined With GMO-SVM[J]. Spectroscopy and Spectral Analysis, 2022, 42(10): 3291
    Download Citation