Laser & Optoelectronics Progress, Volume. 58, Issue 3, 3300041(2021)

Classification of Handkerchief Paper Brand Based on Spectral Data Fusion Technology

Ji Jiahua, Wang Jifen*, and He Xinlong
Author Affiliations
  • School of Investigation, People''s Public Security University of China, Beijing 100038, China
  • show less
    Figures & Tables(9)
    Infrared spectra of handkerchief paper samples
    Raman spectra of handkerchief paper samples
    Trend chart of classification accuracy of 8 brands of handkerchief paper in different dimensions
    Classification accuracy of 14 series of Xinxiangyin handkerchiefs in different dimensions
    • Table 1. LDA accuracy, recall rate and false positive rate of two spectra

      View table

      Table 1. LDA accuracy, recall rate and false positive rate of two spectra

      BrandInfrared spectrumRaman spectrum
      Accuracy/%Recall/%False positive/%Accuracy/%Recall/%False positive/%
      QF92.166.75.396.866.70
      SJ85.766.711.198.488.90
      WD92.166.72.088.966.75.9
      XBB92.155.61.993.777.83.7
      XS90.583.38.893.783.35.3
      XXY92.177.85.690.577.87.4
      XZL93.766.73.598.483.30.0
      YR92.133.31.898.41001.8
    • Table 2. LDA accuracy, recall rate and false positive rate after spectral fusion

      View table

      Table 2. LDA accuracy, recall rate and false positive rate after spectral fusion

      BrandAccuracy/%Recall/%False positive/%
      QF98.483.30
      SJ98.488.90
      WD92.175.03.9
      XBB95.288.93.7
      XS95.283.33.5
      XXY93.788.95.6
      XZL98.483.30
      YR96.883.31.8
    • Table 3. Characteristic variance contribution rate of PCA

      View table

      Table 3. Characteristic variance contribution rate of PCA

      ComponentEigenvalueVariance/%Cumulative variance/%ComponentEigenvalueVariance/%Cumulative variance/%
      PC1437.78948.16248.162PC202.1760.23996.066
      PC2231.31225.44773.608PC212.0960.23196.297
      PC390.8799.99883.606PC222.0230.22396.520
      PC426.0282.86386.470PC231.9180.21196.731
      PC521.1762.33088.799PC241.7860.19696.927
      PC611.2691.24090.039PC251.7020.18797.114
      PC78.2570.90890.947PC261.5870.17597.289
      PC86.4970.71591.662PC271.4810.16397.452
      PC95.0230.55392.215PC281.4250.15797.609
      PC104.1110.45292.667PC291.3820.15297.761
      PC114.0000.44093.107PC301.2890.14297.902
      PC123.7570.41393.520PC311.2520.13898.040
      PC133.7190.40993.929PC321.1830.13098.170
      PC143.4750.38294.311PC331.1540.12798.297
      PC153.1780.35094.661PC341.0890.1298.417
      PC163.0350.33494.995PC351.0240.11398.530
      PC172.7560.30395.298PC360.9520.10598.634
      PC182.5070.27695.574PC370.9140.10198.735
      PC192.3000.25395.827
    • Table 4. Accuracy of LDA in different dimensions

      View table

      Table 4. Accuracy of LDA in different dimensions

      DimensionPrecision/%Overall accuracy/%
      QFSJWDXSXBBXXYXZLYR
      250.011.1055.633.311.166.7025.4
      383.355.68.344.466.733.366.716.742.9
      483.366.716.744.466.733.366.716.746.0
      583.344.433.355.666.744.466.716.749.2
      683.333.325.055.666.755.683.333.350.8
      783.333.350.066.766.766.783.333.358.7
      883.344.450.077.866.766.783.333.361.9
      983.344.458.377.866.766.783.333.363.5
      1083.355.658.377.883.366.783.350.068.3
      1110066.758.377.810066.766.766.773.0
      1210044.450.066.710077.866.766.768.3
      1310044.466.766.710010066.783.376.2
      1483.366.766.777.883.310066.766.776.2
      1583.366.775.077.883.310066.766.777.8
      1683.377.866.788.983.388.966.750.076.2
      1710088.966.788.983.388.966.783.382.5
      1810010083.388.910010010083.393.7
      1910010091.788.910088.983.310093.7
      2010010083.377.810088.910010092.1
      2110010083.388.910088.983.310092.1
      2210010083.388.910010010010095.2
      2310088.983.388.910010010010093.7
      2410010075.088.910010010010093.7
      2510010083.388.910010010010095.2
      2610010091.788.910010010010096.8
      2710010091.788.910010010010096.8
      2810010091.788.910010010010096.8
      2910010091.788.910010010010096.8
      3010010091.788.910010010010096.8
      3110010010088.910010010010098.4
      3210010010088.910010010010098.4
      3310010010088.910010010010098.4
      34100100100100100100100100100
    • Table 5. Comparison results of material and sample

      View table

      Table 5. Comparison results of material and sample

      MaterialQFSJWDXSXBBXXYXZLYR
      JC1
      JC2
    Tools

    Get Citation

    Copy Citation Text

    Ji Jiahua, Wang Jifen, He Xinlong. Classification of Handkerchief Paper Brand Based on Spectral Data Fusion Technology[J]. Laser & Optoelectronics Progress, 2021, 58(3): 3300041

    Download Citation

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

    Category: Spectroscopy

    Received: Jun. 24, 2020

    Accepted: --

    Published Online: Mar. 12, 2021

    The Author Email: Jifen Wang (wangjifen58@126.com)

    DOI:10.3788/LOP202158.0330004

    Topics