• Laser & Optoelectronics Progress
  • Vol. 59, Issue 12, 1210002 (2022)
Jian Zheng, Hao Liu, Xiangchun Yu*, and Chi Zheng
Author Affiliations
  • School of Information and Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi , China
  • show less
    DOI: 10.3788/LOP202259.1210002 Cite this Article Set citation alerts
    Jian Zheng, Hao Liu, Xiangchun Yu, Chi Zheng. Image Exposure Correction Method Based on Inversion Fusion Framework[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1210002 Copy Citation Text show less
    Flow chart of proposed algorithm
    Fig. 1. Flow chart of proposed algorithm
    Contrast between the visual effects of the real haze map and the pseudo-fog map in an underexposed scene. (a) Initial image in an underexposed scene; (b) pseudo-fog map after intensity inversion; (c) real scene haze image
    Fig. 2. Contrast between the visual effects of the real haze map and the pseudo-fog map in an underexposed scene. (a) Initial image in an underexposed scene; (b) pseudo-fog map after intensity inversion; (c) real scene haze image
    Corresponding RGB pixel distribution of the pseudo-fog map and the real fog map. (a) The first column of Fig.2; (b) the second column of Fig.2; (c) the third column of Fig.2
    Fig. 3. Corresponding RGB pixel distribution of the pseudo-fog map and the real fog map. (a) The first column of Fig.2; (b) the second column of Fig.2; (c) the third column of Fig.2
    Image 1 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Fig. 4. Image 1 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Image 2 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Fig. 5. Image 2 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Image 3 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Fig. 6. Image 3 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Image 4 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Fig. 7. Image 4 comparison of experimental results of different exposure correction methods. (a) Original image; (b) RetinexNet algorithm; (c) MBLLEN algorithm; (d) DCP algorithm; (e) LIME algorithm; (f) proposed algorithm
    Comparison of NIQE mean value of correction results
    Fig. 8. Comparison of NIQE mean value of correction results
    Image NO.PSNR /dB
    RetinexNetMBLLENDCPLIMEProposed algorithm
    119.5919.7114.0417.2820.01
    214.9620.2216.6919.7921.42
    320.8613.389.6813.8221.89
    420.4917.8615.4613.2721.02
    Table 1. Comparison of PSNR of each algorithm
    Image NO.Entropy
    RetinexNetMBLLENDCPLIMEProposed algorithm
    17.207.437.737.607.71
    27.717.797.587.837.94
    36.747.717.647.537.72
    46.726.615.576.017.86
    Table 2. Comparison of entropy of each algorithm
    Image NO.AG
    RetinexNetMBLLENDCPLIMEProposed algorithm
    10.03680.03920.04180.05130.0512
    20.04710.03410.03270.04360.0501
    30.03030.04570.04630.04770.0578
    40.01220.00980.00580.00830.0313
    Table 3. Comparison of AG of each algorithm
    Jian Zheng, Hao Liu, Xiangchun Yu, Chi Zheng. Image Exposure Correction Method Based on Inversion Fusion Framework[J]. Laser & Optoelectronics Progress, 2022, 59(12): 1210002
    Download Citation