Laser & Optoelectronics Progress, Volume. 58, Issue 8, 0810001(2021)

Image Enhancement Based on Dual-Channel Prior and Illumination Map Guided Filtering

Xinyu Zhao* and Fuzhen Huang
Author Affiliations
  • College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China
  • show less
    Figures & Tables(11)
    Flow chart of proposed low-illumination enhancement algorithm
    Enhanced images of atmospheric light value via different methods. (a) Original image; (b) method in Ref. [11]; (c) proposed method
    Transmittance images under different α and γ. (a) α=1, γ=0; (b) α=0.75, γ=0.25; (c) α=0.25,γ=0.75; (d) α=0,γ=1
    Edge-extraction images for different bootstrap images. (a) Original image; (b) gray-level inversion image; (c) dark-channel image; (d) illumination images
    Enhancement results after improving transmittance by different methods. (a) Original image; (b) dark-channel; (c) bright-channel; (d) transmittance fusion image; (e) method in Ref. [19]; (f) proposed method
    Enhancement results of low-illumination images with large sky area and obvious change in depth of field for different methods. (a1)--(a4) Original images; (b1)--(b4) method in Ref. [11]; (c1)--(c4) method in Ref. [22]; (d1)--(d4) method in Ref. [23]; (e1)--(e4) proposed method
    Enhancement results of low-illumination images with light source and inhomogeneous light rays for different methods. (a1)--(a3) Original images; (b1)--(b3) method in Ref. [11]; (c1)--(c3) method in Ref. [22]; (d1)--(d3) method in Ref. [23]; (e1)--(e3) proposed method
    • Table 1. Similarity between different bootstrap images and original images

      View table

      Table 1. Similarity between different bootstrap images and original images

      Bootstrap image categorySimilarity
      Gray-level inversion image0.1949
      Dark-channel image0.3940
      Illumination image0.5566
    • Table 2. Information entropies of images

      View table

      Table 2. Information entropies of images

      Original imageMethod in Ref. [11]Method in Ref. [22]Method in Ref. [23]Proposed method
      Fig.6(a1)7.25167.65657.49337.8762
      Fig.6(a2)6.77247.04527.15037.4747
      Fig.6(a3)7.54977.51417.15267.7957
      Fig.6(a4)6.85587.50907.15267.5188
      Fig.7(a1)6.36636.95887.07637.1562
      Fig.7(a2)5.52626.23526.24316.7724
      Fig.7(a3)6.03626.79646.76257.0236
    • Table 3. Average gradients of images

      View table

      Table 3. Average gradients of images

      Original imageMethod in Ref. [11]Method in Ref. [22]Method in Ref. [23]Proposed method
      Fig.6(a1)8.960711.88519.736110.0400
      Fig.6(a2)6.87446.44975.06097.9357
      Fig.6(a3)4.23775.32103.99816.2678
      Fig.6(a4)2.21272.18712.89163.0929
      Fig.7(a1)5.26356.86956.23027.0025
      Fig.7(a2)3.21635.62894.32565.8953
      Fig.7(a3)7.01567.86357.23118.2362
    • Table 4. Structural similarities of images

      View table

      Table 4. Structural similarities of images

      Original imageMethod in Ref. [11]Method in Ref. [22]Method in Ref. [23]Proposed method
      Fig.6(a1)0.52030.59350.49880.6233
      Fig.6(a2)0.40320.52110.42100.5834
      Fig.6(a3)0.59860.65250.55140.6958
      Fig.6(a4)0.52430.69820.62010.7033
      Fig.7(a1)0.57220.58080.41690.6110
      Fig.7(a2)0.55960.51170.46590.5863
      Fig.7(a3)0.42030.52610.30340.5627
    Tools

    Get Citation

    Copy Citation Text

    Xinyu Zhao, Fuzhen Huang. Image Enhancement Based on Dual-Channel Prior and Illumination Map Guided Filtering[J]. Laser & Optoelectronics Progress, 2021, 58(8): 0810001

    Download Citation

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

    Category: Image Processing

    Received: Jul. 22, 2020

    Accepted: Sep. 9, 2020

    Published Online: Apr. 12, 2021

    The Author Email: Xinyu Zhao (15621530269@163.com)

    DOI:10.3788/LOP202158.0810001

    Topics