Underwater image enhancement method based on the generative adversarial network

Abstract. Aiming at the problems of color distortion, nonuniform illumination, and low contrast caused by degradation of underwater images, an underwater image enhancement method (MSFF-GAN) based on generative adversarial network was proposed. A multiscale featured fusion generator is designed, which improves the ability to use different scale features of the model and ensures that the generated image retains more detailed information. The residual dense module is constructed to solve the problem of generator characteristics extracted slower. In the discriminator, to achieve the extraction of local image features, the output matrix is discriminating so that the generated image is closer to the real image. Compared with the existing underwater image enhancement methods qualitatively and quantitatively, the proposed method has better enhancement effect on EUVP and RUIE datasets. The proposed method is superior to the contrast method of three evaluation indexes: PSNR, SSIM, and UIQM.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Hao Xu,et al.  Image Dehazing by Incorporating Markov Random Field with Dark Channel Prior , 2020, Journal of Ocean University of China.

[4]  Rashid Khan.  Underwater Image Restoration Using Fusion and Wavelet Transform Strategy , 2015, J. Comput..

[5]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Xiaoli Yu,et al.  Underwater-GAN: Underwater Image Restoration via Conditional Generative Adversarial Network , 2018, CVAUI/IWCF/MIPPSNA@ICPR.

[8]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Sos S. Agaian,et al.  Human Visual System-Based Image Enhancement and Logarithmic Contrast Measure , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[10]  Chen Gao,et al.  Human-Visual-System-Inspired Underwater Image Quality Measures , 2016, IEEE Journal of Oceanic Engineering.

[11]  Zhipeng Feng,et al.  Underwater Image Enhancement Using Scene Depth-Based Adaptive Background Light Estimation and Dark Channel Prior Algorithms , 2019, IEEE Access.

[12]  Jaihyun Park,et al.  Adaptive Weighted Multi-Discriminator CycleGAN for Underwater Image Enhancement , 2019, Journal of Marine Science and Engineering.

[13]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Na Li,et al.  Multi-scale adversarial network for underwater image restoration , 2019, Optics & Laser Technology.

[15]  Ming Zhu,et al.  Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  Yun Fu,et al.  Residual Dense Network for Image Restoration , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Li Wen,et al.  Towards Real-Time Advancement of Underwater Visual Quality With GAN , 2017, IEEE Transactions on Industrial Electronics.

[18]  Rui-Sheng Jia,et al.  Fast Method of Detecting Tomatoes in a Complex Scene for Picking Robots , 2020, IEEE Access.

[19]  Ying-Ching Chen,et al.  Underwater Image Enhancement by Wavelength Compensation and Dehazing , 2012, IEEE Transactions on Image Processing.

[20]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[21]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[22]  Rui-Sheng Jia,et al.  Fast and Efficient Non-Contact Ball Detector for Picking Robots , 2019, IEEE Access.

[23]  Djemel Ziou,et al.  Image Quality Metrics: PSNR vs. SSIM , 2010, 2010 20th International Conference on Pattern Recognition.

[24]  Jie Li,et al.  WaterGAN: Unsupervised Generative Network to Enable Real-Time Color Correction of Monocular Underwater Images , 2017, IEEE Robotics and Automation Letters.

[25]  Won-Ki Jeong,et al.  Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss , 2017, IEEE Transactions on Medical Imaging.

[26]  Cheolkon Jung,et al.  Automatic Contrast-Limited Adaptive Histogram Equalization With Dual Gamma Correction , 2018, IEEE Access.

[27]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[28]  Md Jahidul Islam,et al.  Fast Underwater Image Enhancement for Improved Visual Perception , 2020, IEEE Robotics and Automation Letters.

[29]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).