Skip to content
2000
Volume 19, Issue 7
  • ISSN: 1872-2121
  • E-ISSN: 2212-4047

Abstract

Background

Due to the difficulty of obtaining the real dataset of paired underwater images, it is urgent to build an unsupervised underwater image enhancement network.

Objective

To address the problem, a novel underwater image enhancement based on Retinex decomposition and Unsupervised Generative Adversarial Network (RUGAN) is proposed.

Methods

A color correction module is proposed considering the different color distortions of underwater images. Further, considering the human visual perception mechanism, the RUGAN network, which is similar to U-Net, is constructed using the characteristics of underwater imaging and Retinex decomposition. Based on Retinex decomposition and the characteristics of underwater imaging, the RUGAN network similar to U-Net is constructed. The reflectance image and illumination image are obtained. The reflectance image with a better effect is taken as the enhancement result. Unlike the previous supervised methods, RUGAN adopts clear air images and distorted underwater images as training. RUGAN adopts the underwater image of the color correction module as pseudo-ground truth to achieve an unsupervised effect.

Results

The superiority of RUGAN network is further supported by extensive experiments that compared it with more methods.

Conclusion

The RUGAN performs well both subjectively and objectively.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/eng/10.2174/0118722121231723231005112802
2023-10-27
2025-09-13

  • From This Site

    /content/journals/eng/10.2174/0118722121231723231005112802
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. FanB. Dual refinement underwater object detection network.Computer Vision – ECCV.ChamSpringer202010.1007/978‑3‑030‑58565‑5_17
     [Google Scholar]
  2. HummelR. Image enhancement by histogram transformation.Comput. Graph. Image Process.19776218419510.1016/S0146‑664X(77)80011‑7
     [Google Scholar]
  3. PizerS.M. JohnstonR.E. EricksenJ.P. YankaskasB.C. MüllerK.E. Contrast-limited adaptive histogram equalization: Speed and effectiveness.Proceedings of the First Conference on Visualization in Biomedical Computing, 1990 Atlanta, GA, USA10.1109/VBC.1990.109340
     [Google Scholar]
  4. Yung-ChengL. Wen-HsinC. Ye-QuangC. Automatic white balance for digital still camera.IEEE Trans. Consum. Electron.199541346046610.1109/30.468045
     [Google Scholar]
  5. AncutiC. AncutiC.O. HaberT. BekaertP. Enhancing underwater images and videos by fusion.2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012 Providence, RI, USA10.1109/CVPR.2012.6247661
     [Google Scholar]
  6. AncutiC.O. AncutiC. De VleeschouwerC. BekaertP. Color balance and fusion for underwater image enhancement.IEEE Trans. Image Process.201827137939310.1109/TIP.2017.275925228981416
     [Google Scholar]
  7. AncutiC.O. AncutiC. De VleeschouwerC. SbertM. Color channel compensation (3C): A fundamental pre-processing step for image enhancement.IEEE Trans. Image Process.2020292653266510.1109/TIP.2019.295130431751271
     [Google Scholar]
  8. KaimingH. JianH. XiaoouT. Single image haze removal using dark channel prior.IEEE Trans. Pattern Anal. Mach. Intell.201133122341235310.1109/TPAMI.2010.16820820075
     [Google Scholar]
  9. DrewsP. NascimentoE. MoraesF. BotelhoS. CamposM. Transmission estimation in underwater single images2013 IEEE International Conference on Computer Vision Workshops, 2013 Sydney, NSW, Australia10.1109/ICCVW.2013.113
     [Google Scholar]
  10. PengY.T. CosmanP.C. Underwater image restoration based on image blurriness and light absorption.IEEE Trans. Image Process.20172641579159410.1109/TIP.2017.266384628182556
     [Google Scholar]
  11. PengY.T. CaoK. CosmanP.C. Generalization of the dark channel prior for single image restoration.IEEE Trans. Image Process.20182762856286810.1109/TIP.2018.281309229570087
     [Google Scholar]
  12. BermanD. LevyD. AvidanS. TreibitzT. Underwater single image color restoration using haze-lines and a new quantitative dataset.IEEE Trans. Pattern Anal. Mach. Intell.20214382822283732142424
     [Google Scholar]
  13. LiJ. SkinnerK.A. EusticeR.M. Johnson-RobersonM. WaterGAN: Unsupervised generative network to enable real-time color correction of monocular underwater images.IEEE Robot. Autom. Lett.201831387394
     [Google Scholar]
  14. FabbriC. IslamM.J. SattarJ. Enhancing underwater imagery using generative adversarial networks2018 IEEE International Conference on Robotics and Automation (ICRA), 2018 Brisbane, QLD, Australia10.1109/ICRA.2018.8460552
     [Google Scholar]
  15. ZhuJ-Y. ParkT. IsolaP. EfrosA-A. Unpaired image-to-image translation using cycle-consistent adversarial networksProc. Int. Conf. Comput. Vis.2017pp. 2242-2251 Venice, Italy10.1109/ICCV.2017.244
     [Google Scholar]
  16. IsolaP. ZhuJ-Y. ZhouT. EfrosA-A. Image-to-image translation with conditional adversarial networksProc. IEEE Conf. Comput. Vis. Pattern Recognit.2017pp. 5967-5976 Hawaii, USA
     [Google Scholar]
  17. RonnebergerP. Fischer BroxT. U-Net: Convolutional networks for biomedical image segmentation.Medical Image Computing and Computer-Assisted InterventionNew York, NY, USASpringer2015234241
     [Google Scholar]
  18. LiC. AnwarS. PorikliF. Underwater scene prior inspired deep underwater image and video enhancement.Pattern Recognit.20209810703810704910.1016/j.patcog.2019.107038
     [Google Scholar]
  19. GuoY. LiH. ZhuangP. Underwater image enhancement using a multiscale dense generative adversarial network.IEEE J. Oceanic Eng.202045386287010.1109/JOE.2019.2911447
     [Google Scholar]
  20. LiH. LiJ. WangW. A fusion adversarial underwater image enhancement network with a public test dataset.arXiv:1906.068192019
     [Google Scholar]
  21. LiC. GuoC. RenW. CongR. HouJ. KwongS. TaoD. An underwater image enhancement benchmark dataset and beyond.IEEE Trans. Image Process.2020294376438910.1109/TIP.2019.295524131796402
     [Google Scholar]
  22. ChongyiL. XuH. LinC. Underwater image enhancement via medium transmission-guided multi-color space embedding.IEEE Transactions on Image Processing20213049855000
     [Google Scholar]
  23. LiC. GuoJ. GuoC. Emerging from water: Underwater image color correction based on weakly supervised color transfer.IEEE Signal Process. Lett.201825332332710.1109/LSP.2018.2792050
     [Google Scholar]
  24. Zhibin, H. RuyueY. Underwater image enhancement method for generating countermeasure network based on conditionsC.N. Patent 111833268A2023
     [Google Scholar]
  25. LandE.H. McCannJ.J. Lightness and retinex theory.J. Opt. Soc. Am.197161111110.1364/JOSA.61.0000015541571
     [Google Scholar]
  26. GaldranA. On the duality between retinex and image dehazing.Proc. IEEE Conf. Comput. Vis. Pattern Recognit2018 pp. 8212-822110.1109/CVPR.2018.00857
     [Google Scholar]
  27. WeiChen Deep retinex decomposition for low-light enhancement.arXiv:1808.045602018
     [Google Scholar]
  28. MaoX. LiQ. XieH. LauR-Y. WangZ. SmolleyS-P. Least squares generative adversarial networks.Int. Conf. Comput. Vis., 2017pp. 2794-2802 Venice, Italy
     [Google Scholar]
  29. DengJ. DongW. SocherR. LiL-J. LiK. Fei-FeiL. ImageNet: A large-scale hierarchical image database.2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009 Miami, FL, USA10.1109/CVPR.2009.5206848
     [Google Scholar]
  30. ZhaoH. OrazioG. IuriF. JanK. Loss functions for neural networks for image processing.arXiv:1511.088612015
     [Google Scholar]
  31. KingmaD. BaJ. Adam: A method for stochastic optimization.3rd International Conference for Learning Representations, 2014 San Diego
     [Google Scholar]
  32. YangM. SowmyaA. An underwater color image quality evaluation metric.IEEE Trans. Image Process.201524126062607110.1109/TIP.2015.249102026513783
     [Google Scholar]
  33. PanettaK. GaoC. AgaianS. Human-visual-system-inspired underwater image quality measures.IEEE J. Oceanic Eng.201641354155110.1109/JOE.2015.2469915
     [Google Scholar]
  34. CannyJ. A computational approach to edge detection.IEEE Trans. Pattern Anal. Mach. Intell.1986PAMI-8667969810.1109/TPAMI.1986.476785121869365
     [Google Scholar]
  35. PengH. LiB. LingH. HuW. XiongW. MaybankS.J. Salient object detection via structured matrix decomposition.IEEE Trans. Pattern Anal. Mach. Intell.201739481883210.1109/TPAMI.2016.256262628113696
     [Google Scholar]
/content/journals/eng/10.2174/0118722121231723231005112802
Loading
Underwater Image Enhancement based on Retinex Decomposition and Unsupervised Generative Adversarial Networks
Recent Pat Eng 19, E271023222797 (2025); https://doi.org/10.2174/0118722121231723231005112802
/content/journals/eng/10.2174/0118722121231723231005112802
/content/journals/eng/10.2174/0118722121231723231005112802
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): generative adversarial networks; illumination image; reflectance image; Retinex decomposition; underwater image enhancement; unsupervised

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test