Abstract
The underwater optical imaging environment presents unique challenges due to its complexity. This paper addresses the limitations of existing algorithms in handling underwater images captured in artificial light scenes. We proposed an underwater artificial light optimization algorithm to preprocess images with uneven lighting, mitigating the effects of light distortion. Furthermore, we proposed a novel underwater image enhancement algorithm based the Multiscale Fusion Generative Adversarial Network, named UMSGAN, to address the issues of low contrast and color distortion. UMSGAN uses the generative adversarial network as the underlying framework and first extracts information from the degraded image through three parallel branches separately, and adds residual dense blocks in each branch to learn deeper features. Subsequently, the features extracted from the three branches are fused and the detailed information of the image is recovered by the reconstruction module, named RM. Finally, multiple loss functions are linearly superimposed, and the adversarial network is trained iteratively to obtain the enhanced underwater images. The algorithm is designed to accommodate various underwater scenes, providing both color correction and detail enhancement. We conducted a comprehensive evaluation of the proposed algorithm, considering both qualitative and quantitative aspects. The experimental results demonstrate the effectiveness of our approach on a diverse underwater image dataset. The proposed algorithm exhibits superior performance in terms of enhancing underwater image quality, achieving significant improvements in contrast, color accuracy, and detail preservation. The proposed methodology exhibits promising results, offering potential applications in various domains such as underwater photography, marine exploration, and underwater surveillance.
Similar content being viewed by others
Data availability
The datasets analysed during the current study are available in the Github repository, https://github.com/xahidbuffon/funie-gan. The datasets generated during the current study are available from the corresponding author on reasonable request.
References
Yi X, Walia E, Babyn P (2019) Generative adversarial network in medical imaging: a review. Med Image Anal. https://doi.org/10.1016/j.media.2019.101552
Khaldi Y, Benzaoui A (2020) A new framework for grayscale ear images recognition using generative adversarial networks under unconstrained conditions. Evol Syst. https://doi.org/10.1007/s12530-020-09346-1
Guo C, Li C, Guo J, Cong R, Fu H, Han P (2019) Hierarchical Features Driven Residual Learning for Depth Map Super-Resolution. In: IEEE transactions on image processing. https://doi.org/10.1109/TIP.2018.2887029
Li Y, Li J, Li Y, Kim H, Serikawa S (2019) Low-light underwater image enhancement for deep-sea tripod. In: IEEE Access. https://doi.org/10.1109/ACCESS.2019.2897691
Hou M, Liu R, Fan X, Luo Z (2018) Joint residual learning for underwater image enhancement. In: 2018 25th IEEE international conference on image processing (ICIP). https://doi.org/10.1109/ICIP.2018.8451209
Zhang S, Wang T, Dong J, Yu H (2017) Underwater image enhancement via extended multi-scale retinex. Neurocomputing. https://doi.org/10.1016/j.neucom.2017.03.029
Fabbri C, Islam MJ, Sattar J (2018) Enhancing underwater imagery using generative adversarial networks. In: Proc. IEEE Int. Conf. Robot. Automat 7159–7165.
Wang Y, Fan H et al (2021) BA-GAN: Block Attention GAN model for Underwater Image Enhancement. In: Proc. ICUS. https://doi.org/10.1109/ICUS52573.2021.9641455
Song W, Jing XJ et al (2021) Underwater image enhancement based on generative adversarial network with preprocessed image penalty. Laser & Optoelectronics Progress. 1006–4125
Estrada DC, Dalgleish FR et al (2022) Underwater LiDAR image enhancement using a GAN based machine learning technique. IEEE Sens J. https://doi.org/10.1109/JSEN.2022.3146133
Islam MJ, Xia Y, Sattar J (2020) Fast underwater image enhancement for improved visual perception. IEEE Robotics and Automation Letters. https://doi.org/10.1109/LRA.2020.2974710
Muthuraman DL, Santhanam SM (2021) Visibility improvement of underwater turbid image using hybrid restoration network with weighted filter. Multidimension Syst Signal Process. https://doi.org/10.1007/s11045-021-00795-8
Farbman Z, Fattal R, Lischinski D et al (2008) Edge-preserving decompositions for multi-scale tone and detail manipulation. Acm Trans Graph 10(1145/1360612):1360666
Li C, Guo C et al (2019) An underwater image enhancement benchmark dataset and beyond. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2019.2955241
Qi Q, Zhang Y et al (2022) Underwater image co-enhancement with correlation feature matching and joint learning. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2021.3074197
Drews JP, Nascimento E et al (2013) Transmission Estimation in Underwater Single Images. In: Proc. ICCVW. https://doi.org/10.1109/ICCVW.2013.113
Hanmante BP, Ingle M (2018) Underwater image restoration based on light absorption. In: Proc. ICCUBEA
Wei S, Yan W et al (2018) A rapid scene depth estimation model based on underwater light attenuation prior for underwater image restoration. In: Proc. https://doi.org/10.1007/978-3-030-00776-8_62
Liu S, Fan H et al (2022) Adaptive learning attention network for underwater image enhancement. In: IEEE Robot Auto Lett. https://doi.org/10.1109/LRA.2022.3156176
Chen XL, Zhang P, Quan LW et al (2021) Underwater image enhancement based on deep learning and image formation model. arXiv. https://doi.org/10.48550/arXiv.2101.00991
Gonzalez-sabbagh S, Robles-kelly A, Gao S (2022) DGD-cGAN:a Dual Generator for Image Dewatering and Restoration. arXiv. https://doi.org/10.48550/arXiv.2211.10026
Jiang CQ, Xue Z (2019) Application of hybrid residual learning and guided filtering algorithm in image defogging. Opt Precision Eng 2702−2712
Isola P, Zhu JY et al (2016) Image-to-image translation with conditional adversarial networks. IEEE. https://doi.org/10.1109/CVPR.2017.632
Mirza M, Osindero S (2014) Conditional generative adversarial nets. Comput Sci. https://doi.org/10.48550/arXiv.1411.1784
Li C, Wand M (2016) Precomputed real-time texture synthesis with markovian generative adversarial networks. Springer. https://doi.org/10.1007/978-3-319-46487-9_43
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Comput Vis Pattern Recognit. https://doi.org/10.48550/arXiv.1409.1556
Zhou Y, Yan KM, Li XF (2022) Underwater image enhancement via physical-feedback adversarial transfer learning. IEEE J Oceanic Eng. https://doi.org/10.1109/JOE.2021.3104055
Sankur LB (2002) Statistical evaluation of image quality measures. J Electron Imaging 10(1117/1):1455011
Zhou W, Bovik AC et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2003.819861
Peng YT, Cosman PC (2017) Underwater image restoration based on image blurriness and light absorption. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2017.2663846
Yang M, Sowmya A (2015) An underwater color image quality evaluation metric. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2015.2491020
Ma H, Xin J, Chen, et al (2018) Speckle noise reduction in optical coherence tomography images based on edge-sensitive cGAN. Biomed Opt Express. https://doi.org/10.1364/BOE.9.005129
Jian M, Liu X, Luo H (2021) Underwater image processing and analysis: a review. Signal Process Image Commun. https://doi.org/10.1016/j.image.2020.116088
Yang M, Hu K, Du YX, Wei ZQ et al (2020) Underwater image enhancement based on conditional generative adversarial network. Signal Process. https://doi.org/10.1016/j.image.2019.115723
Langenkmper D, Kevelaer VR, Purser A et al (2020) Gear-induced concept drift in marine images and its effect on deep learning classification. Front Mar Sci. https://doi.org/10.3389/fmars.2020.00506
Xiao J, Zhang S, Yao Y et al (2022) Generative adversarial network with hybrid attention and compromised normalization for multi-scene image conversion. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06841-7
Wang Z, Xuan J, Shi T (2022) A novel semi-supervised generative adversarial network based on the actor-critic algorithm for compound fault recognition. Neural Comput Appl. https://doi.org/10.1007/s00521-022-07011-z
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dai, Y., Wang, J., Wang, H. et al. Underwater image enhancement based on multiscale fusion generative adversarial network. Int. J. Mach. Learn. & Cyber. 15, 1331–1341 (2024). https://doi.org/10.1007/s13042-023-01970-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01970-y