Laser & Optoelectronics Progress, Volume. 55, Issue 6, 061005(2018)

Stereoscopic Image Quality Assessment Based on Wavelet Transform and Structure Characteristics

Chunping Hou and Honghu Lin*;
Author Affiliations
  • School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
  • show less
    Figures & Tables(9)
    Flowchart of the proposed algorithm
    Wavelet decomposition
    Dual-tree complex wavelet transform
    Different types of distortion images
    Feature distributions of 5 distortion types on an image. (a) Phase amplitude distribution; (b) gradient distribution
    Prediction model of image quality
    • Table 1. Performance comparison of algorithms

      View table

      Table 1. Performance comparison of algorithms

      AlgorithmLIVE3 DIQD Phase 1LIVE3 DIQD Phase 2
      SROCCPLCCRMSESROCCPLCCRMSE
      FSIM0.91350.92706.01040.78740.79776.4984
      MS-SSIM0.92330.92526.22450.77070.77587.1221
      VIF0.90870.91176.73680.71670.78656.9708
      Ref. [24]0.85590.86458.24240.63750.65848.4956
      Ref. [21]0.92510.93505.81550.84940.86285.7058
      Ref. [11]0.93470.93885.64700.89350.91134.6480
      Ref. [22]0.89200.88706.99500.82500.81806.5000
      Ref. [23]0.38300.626014.82700.54300.56809.2940
      Proposed0.93360.94405.37180.90740.92154.3821
    • Table 2. Single distortion performance comparison on LIVE3 DIQD Phase 1

      View table

      Table 2. Single distortion performance comparison on LIVE3 DIQD Phase 1

      DistortionCriteriaFSIMMS-SSIMVIFRef. [24]Ref. [21]Ref. [11]Ref. [22]Ref. [23]Proposed
      JP2KPLCC0.91880.91880.93730.83810.92130.95200.84800.90500.9716
      SROCC0.90380.89170.90150.83880.89450.91270.83700.86600.9279
      RMSE4.50516.81416.01687.0658-3.9631--3.0330
      JPEGPLCC0.62340.68596.01680.28660.52000.75460.62600.72900.8712
      SROCC0.57720.61230.58070.09310.49510.71640.63800.67500.8117
      RMSE4.83946.34456.40976.2650-4.2912--3.0953
      WNPLCC0.92836.34450.92030.92800.94480.92660.92500.90400.9617
      SROCC0.93450.93200.92210.92840.94050.92890.93100.91400.9314
      RMSE5.64018.04138.67816.1964-6.2569--4.3513
      G blurPLCC0.93700.94350.95680.94750.95920.95830.89900.61700.9573
      SROCC0.92230.92610.93410.93450.94030.93320.83300.55500.8667
      RMSE4.80196.39735.41614.6291-4.1371--4.0158
      FFPLCC0.78390.80180.86000.70860.85940.86200.70700.50300.8431
      SROCC0.72980.72310.80420.47090.79630.82860.64900.64000.7265
      RMSE7.17599.89978.45378.7671-6.2993--6.3050
    • Table 3. Comparison of computation time

      View table

      Table 3. Comparison of computation time

      AlgorithmFSIM[9]MS-SSIM[19]VIF[20]Ref. [24]Proposed
      Time cost /s1.77710.94261.67260.750319.1035
    Tools

    Get Citation

    Copy Citation Text

    Chunping Hou, Honghu Lin. Stereoscopic Image Quality Assessment Based on Wavelet Transform and Structure Characteristics[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061005

    Download Citation

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

    Category: Image Processing

    Received: Nov. 2, 2017

    Accepted: --

    Published Online: Sep. 11, 2018

    The Author Email: Honghu Lin ( linhonghu@tju.edu.cn)

    DOI:10.3788/LOP55.061005

    Topics