• Laser & Optoelectronics Progress
  • Vol. 60, Issue 14, 1410003 (2023)
Yuntao Zhang1, Huiping Liu1、*, Yiming Huang2, and Jia Yu1
Author Affiliations
  • 1College of Physics and Optoelectronic Engineering, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, Shandong, China
  • 2College of Optical Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China
  • show less
    DOI: 10.3788/LOP221820 Cite this Article Set citation alerts
    Yuntao Zhang, Huiping Liu, Yiming Huang, Jia Yu. Underwater Image Enhancement Based on Image Segmentation and Color Adaptation Transformation for White Balance[J]. Laser & Optoelectronics Progress, 2023, 60(14): 1410003 Copy Citation Text show less
    Flow chart of proposed algorithm
    Fig. 1. Flow chart of proposed algorithm
    Low illumination image processing. (a) Original image[7]; (b) negative image; (c) negative image after defogging; (d) enhancement result
    Fig. 2. Low illumination image processing. (a) Original image[7]; (b) negative image; (c) negative image after defogging; (d) enhancement result
    Contrast of white balance effect based on color adaptation transformation. (a) Original image; (b) white balance after square linear gain adjustment; (c) white balance effect after BFD transformation
    Fig. 3. Contrast of white balance effect based on color adaptation transformation. (a) Original image; (b) white balance after square linear gain adjustment; (c) white balance effect after BFD transformation
    Flow chart of color adaptation and white balance effect
    Fig. 4. Flow chart of color adaptation and white balance effect
    Comparison of subjective evaluation
    Fig. 5. Comparison of subjective evaluation
    ImageAngular error averageAngular error variance
    Original image27.64062.1759
    Gray-World with linear stretching6.04519.1292
    Gray-World with BFD transformation2.45871.7430
    Table 1. Comparison between linear stretching and BFD transformation
    ImageAngular error averageAngular error variance
    Original image3.03125.7248
    Single Gray-World2.75888.1877
    Single SOG4.62354.9296
    Single GE9.39601.7924
    SOG with Gray-World3.23813.9409
    GE with Gray-World4.05691.7149
    Table 2. Angular error of different combinations of white balance algorithms
    ImageUDCPHaze-LineProposed algorithm
    RGT_29930.48770.53440.592096179
    RGT_29980.42520.50590.577622
    RGT_30000.42200.48050.57214
    RGT_30080.43140.49610.572212
    RGT_30140.43440.49880.591271
    RGT_30230.49930.55450.624392
    RGT_30300.46220.54000.551507
    RGT_31580.45230.51380.544262
    RGT_32040.47600.52260.602165
    RGT_32720.53180.55020.610868
    RGT_32740.49410.50810.584179
    Average0.46510.51860.5839
    Table 3. [in Chinese]
    ImageUDCPHaze-LineProposed algorithm
    RGT_29930.7816620.9313616061.350293899
    RGT_29980.741460.9486861.392445
    RGT_30000.7272690.9287741.437608
    RGT_30080.7507270.8731351.415518
    RGT_30140.7811650.9385471.424818
    RGT_30231.0237311.1556121.460377
    RGT_30300.6568961.0039311.185824
    RGT_31580.8873321.0232991.304773
    RGT_32040.6835940.8581911.300116
    RGT_32720.9581111.0678511.387233
    RGT_32740.9204830.99271.398582
    Average0.8102210.9747351.368872
    Table 4. UIQM evaluation index
    ImageUDCPHaze-LineProposed algorithm
    Angular error averageAngular error varianceAngular error averageAngular error variance

    Angular

    error average

    Angular error variance
    RGT_299333.046918.094.753613.64473.608310.7422
    RGT_299835.73480.176111.32101.43011.91590.2676
    RGT_300033.61879.04745.24414.47373.72184.1903
    RGT_300834.37351.457415.340419.67513.03012.5805
    RGT_301434.56771.49273.17600.88209.68296.9542
    RGT_320434.95042.08979.04386.90384.936012.2257
    RGT_327235.82650.10869.20379.53808.453711.6362
    RGT_327435.90190.12846.22720.98745.42888.0949
    Average34.75264.07388.03877.19195.09727.0865
    Table 5. Angular error evaluation
    Yuntao Zhang, Huiping Liu, Yiming Huang, Jia Yu. Underwater Image Enhancement Based on Image Segmentation and Color Adaptation Transformation for White Balance[J]. Laser & Optoelectronics Progress, 2023, 60(14): 1410003
    Download Citation