Optics and Precision Engineering, Volume. 29, Issue 10, 2444(2021)

Intelligent evaluation of grotto surface weathering based on spectral chromatic aberration and principal component feature fusion

Chi-peng CAO1... Hui-qin WANG1,*, Ke WANG1, Zhan WANG2, Gang ZHANG2 and Tao MA2 |Show fewer author(s)
Author Affiliations
  • 1School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an70055, China
  • 2Shanxi Provincial Institute of Cultural Relics Protection, Xi’an710075, China
  • show less
    Figures & Tables(13)
    Reflection spectrum characterization of different weathering types and degrees on the surface of grotto
    Multi-spectral imaging data of weathering area on the surface of grotto
    Technical block diagram of intelligent evaluation method for grotto surface weathering
    Reconstructed spectral characteristic curve of grotto surface
    Principal component analysis results of multi-spectral image of cave surface weathering
    Principal component analysis results image color image image
    Overall evaluation results of weathering on the surface of grotto
    • Table 1. Changes of L*a*b, XYZ and RGB in different weathering types and weathering degree areas

      View table
      View in Article

      Table 1. Changes of L*a*b, XYZ and RGB in different weathering types and weathering degree areas

      Weathering typeWstrong1Wstrong2Wweak1Wweak2Wslightly1Wslightly2Wdust1Wdust2Wbenchmark
      L*46.443.742.637.733.028.08.07.90
      a*3.54.73.53.13.62.50.20.20
      b*8.910.58.38.79.07.67.97.80
      X15.713.913.010.07.75.50.80.80
      Y15.613.612.99.97.55.50.90.90
      Z9.88.18.16.04.43.20.30.30
      R12111711198887427270
      G1081009887756423230
      B95858674635510100
    • Table 2. Color difference judgment standard

      View table
      View in Article

      Table 2. Color difference judgment standard

      ΔEChromatic aberration degree identification
      0~0.5Trace
      0.5~1.5Lightweight
      1.5~3.0Can feel
      3.0~6.0obvious
      6.0~12.0tremendous
      12.0huge
    • Table 3. Color difference between different weathering types and weathering degrees and reference points

      View table
      View in Article

      Table 3. Color difference between different weathering types and weathering degrees and reference points

      Color difference typeWstrong-WbenchmarkWweak-WbenchmarkWslightly-WbenchmarkWdust-Wbenchmark
      ΔE7645.1938.8129.1211.24
      ΔE9445.1938.8129.1211.24
      ΔE2 00032.3727.0119.578.2
    • Table 4. Color difference between different weathering types and degrees

      View table
      View in Article

      Table 4. Color difference between different weathering types and degrees

      Color difference typeWstrongWweakWslightlyWdustWbenchmark
      Wstrong05.8312.6821.0174.05
      Wweak5.8306.855.8368.22
      Wslightly12.686.8508.3361.37
      Wdust21.0115.188.33053.04
      Wbenchmark74.0568.2261.3753.040
    • Table 5. Contribution rate and cumulative contribution rate of the first three principal components

      View table
      View in Article

      Table 5. Contribution rate and cumulative contribution rate of the first three principal components

      Principal componentEigenvaluesContribution rateCumulative contribution rate
      PC116757.9095.41%95.41%
      PC2579.803.30%98.71%
      PC392.210.53%99.24%
    • Table 6. Comparison of accuracy and kappa coefficient of four evaluation methods

      View table
      View in Article

      Table 6. Comparison of accuracy and kappa coefficient of four evaluation methods

      MethodAccuracy evaluationColor difference-principal componentReflectance spectrumprincipal componentColor difference
      RFTraining accuracy100.00%99.91%98.52%93.03%
      Prediction accuracy99.86%98.49%91.34%70.26%
      Kappa coefficient0.990.980.890.53
      KNNTraining accuracy99.79%94.99%88.60%75.43%
      Prediction accuracy97.50%91.69%82.68%66.84%
      Kappa coefficient0.960.900.690.42
      BPTraining accuracy63.93%63.19%46.13%36.84%
      Prediction accuracy50.81%48.00%42.19%32.51%
      Kappa coefficient0.280.250.210.18
      RBFTraining accuracy96.12%95.95%87.52%70.08%
      Prediction accuracy94.73%92.88%85.96%65.84%
      Kappa coefficient0.920.910.750.39
    Tools

    Get Citation

    Copy Citation Text

    Chi-peng CAO, Hui-qin WANG, Ke WANG, Zhan WANG, Gang ZHANG, Tao MA. Intelligent evaluation of grotto surface weathering based on spectral chromatic aberration and principal component feature fusion[J]. Optics and Precision Engineering, 2021, 29(10): 2444

    Download Citation

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

    Category: Information Sciences

    Received: Feb. 9, 2021

    Accepted: --

    Published Online: Nov. 23, 2021

    The Author Email: WANG Hui-qin (hqwang@xauat.edu.cn)

    DOI:10.37188/OPE.20212910.2444

    Topics