Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network
The complex underwater environment and light scattering effect lead to severe degradation problems in underwater images, such as color distortion, noise interference, and loss of details. However, the degradation problems of underwater images bring a significant challenge to underwater applications....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/6/1124 |
| _version_ | 1797594019178479616 |
|---|---|
| author | Peng Yang Chunhua He Shaojuan Luo Tao Wang Heng Wu |
| author_facet | Peng Yang Chunhua He Shaojuan Luo Tao Wang Heng Wu |
| author_sort | Peng Yang |
| collection | DOAJ |
| description | The complex underwater environment and light scattering effect lead to severe degradation problems in underwater images, such as color distortion, noise interference, and loss of details. However, the degradation problems of underwater images bring a significant challenge to underwater applications. To address the color distortion, noise interference, and loss of detail problems in underwater images, we propose a triple-branch dense block-based generative adversarial network (TDGAN) for the quality enhancement of underwater images. A residual triple-branch dense block is designed in the generator, which improves performance and feature extraction efficiency and retains more image details. A dual-branch discriminator network is also developed, which helps to capture more high-frequency information and guides the generator to use more global content and detailed features. Experimental results show that TDGAN is more competitive than many advanced methods from the perspective of visual perception and quantitative metrics. Many application tests illustrate that TDGAN can significantly improve the accuracy of underwater target detection, and it is also applicable in image segmentation and saliency detection. |
| first_indexed | 2024-03-11T02:17:40Z |
| format | Article |
| id | doaj.art-b9f8bc5e498c4a32b657f11e5b7fbb4f |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T02:17:40Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-b9f8bc5e498c4a32b657f11e5b7fbb4f2023-11-18T11:06:14ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-05-01116112410.3390/jmse11061124Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial NetworkPeng Yang0Chunhua He1Shaojuan Luo2Tao Wang3Heng Wu4Guangdong Provincial Key Laboratory of Cyber-Physical System, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaGuangdong Provincial Key Laboratory of Cyber-Physical System, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Chemical Engineering and Light Industry, Guangdong University of Technology, Guangzhou 510006, ChinaGuangdong Provincial Key Laboratory of Cyber-Physical System, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaGuangdong Provincial Key Laboratory of Cyber-Physical System, School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaThe complex underwater environment and light scattering effect lead to severe degradation problems in underwater images, such as color distortion, noise interference, and loss of details. However, the degradation problems of underwater images bring a significant challenge to underwater applications. To address the color distortion, noise interference, and loss of detail problems in underwater images, we propose a triple-branch dense block-based generative adversarial network (TDGAN) for the quality enhancement of underwater images. A residual triple-branch dense block is designed in the generator, which improves performance and feature extraction efficiency and retains more image details. A dual-branch discriminator network is also developed, which helps to capture more high-frequency information and guides the generator to use more global content and detailed features. Experimental results show that TDGAN is more competitive than many advanced methods from the perspective of visual perception and quantitative metrics. Many application tests illustrate that TDGAN can significantly improve the accuracy of underwater target detection, and it is also applicable in image segmentation and saliency detection.https://www.mdpi.com/2077-1312/11/6/1124generative adversarial network (GAN)underwater image enhancementmultiscale denseresidual learning |
| spellingShingle | Peng Yang Chunhua He Shaojuan Luo Tao Wang Heng Wu Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network Journal of Marine Science and Engineering generative adversarial network (GAN) underwater image enhancement multiscale dense residual learning |
| title | Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network |
| title_full | Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network |
| title_fullStr | Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network |
| title_full_unstemmed | Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network |
| title_short | Underwater Image Enhancement via Triple-Branch Dense Block and Generative Adversarial Network |
| title_sort | underwater image enhancement via triple branch dense block and generative adversarial network |
| topic | generative adversarial network (GAN) underwater image enhancement multiscale dense residual learning |
| url | https://www.mdpi.com/2077-1312/11/6/1124 |
| work_keys_str_mv | AT pengyang underwaterimageenhancementviatriplebranchdenseblockandgenerativeadversarialnetwork AT chunhuahe underwaterimageenhancementviatriplebranchdenseblockandgenerativeadversarialnetwork AT shaojuanluo underwaterimageenhancementviatriplebranchdenseblockandgenerativeadversarialnetwork AT taowang underwaterimageenhancementviatriplebranchdenseblockandgenerativeadversarialnetwork AT hengwu underwaterimageenhancementviatriplebranchdenseblockandgenerativeadversarialnetwork |