An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index
When underwater vehicles work, underwater images are often absorbed by light and scattered and diffused by floating objects, which leads to the degradation of underwater images. The generative adversarial network (GAN) is widely used in underwater image enhancement tasks because it can complete imag...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/9/7/691 |
| _version_ | 1827688969943384064 |
|---|---|
| author | Kai Hu Yanwen Zhang Chenghang Weng Pengsheng Wang Zhiliang Deng Yunping Liu |
| author_facet | Kai Hu Yanwen Zhang Chenghang Weng Pengsheng Wang Zhiliang Deng Yunping Liu |
| author_sort | Kai Hu |
| collection | DOAJ |
| description | When underwater vehicles work, underwater images are often absorbed by light and scattered and diffused by floating objects, which leads to the degradation of underwater images. The generative adversarial network (GAN) is widely used in underwater image enhancement tasks because it can complete image-style conversions with high efficiency and high quality. Although the GAN converts low-quality underwater images into high-quality underwater images (truth images), the dataset of truth images also affects high-quality underwater images. However, an underwater truth image lacks underwater image enhancement, which leads to a poor effect of the generated image. Thus, this paper proposes to add the natural image quality evaluation (NIQE) index to the GAN to provide generated images with higher contrast and make them more in line with the perception of the human eye, and at the same time, grant generated images a better effect than the truth images set by the existing dataset. In this paper, several groups of experiments are compared, and through the subjective evaluation and objective evaluation indicators, it is verified that the enhanced image of this algorithm is better than the truth image set by the existing dataset. |
| first_indexed | 2024-03-10T10:07:04Z |
| format | Article |
| id | doaj.art-f766c87f300442c7bcf843668c9af3b0 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T10:07:04Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-f766c87f300442c7bcf843668c9af3b02023-11-22T01:29:56ZengMDPI AGJournal of Marine Science and Engineering2077-13122021-06-019769110.3390/jmse9070691An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation IndexKai Hu0Yanwen Zhang1Chenghang Weng2Pengsheng Wang3Zhiliang Deng4Yunping Liu5School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaWhen underwater vehicles work, underwater images are often absorbed by light and scattered and diffused by floating objects, which leads to the degradation of underwater images. The generative adversarial network (GAN) is widely used in underwater image enhancement tasks because it can complete image-style conversions with high efficiency and high quality. Although the GAN converts low-quality underwater images into high-quality underwater images (truth images), the dataset of truth images also affects high-quality underwater images. However, an underwater truth image lacks underwater image enhancement, which leads to a poor effect of the generated image. Thus, this paper proposes to add the natural image quality evaluation (NIQE) index to the GAN to provide generated images with higher contrast and make them more in line with the perception of the human eye, and at the same time, grant generated images a better effect than the truth images set by the existing dataset. In this paper, several groups of experiments are compared, and through the subjective evaluation and objective evaluation indicators, it is verified that the enhanced image of this algorithm is better than the truth image set by the existing dataset.https://www.mdpi.com/2077-1312/9/7/691underwater image enhancementgenerative adversarial networknatural image quality evaluation indexthe true image |
| spellingShingle | Kai Hu Yanwen Zhang Chenghang Weng Pengsheng Wang Zhiliang Deng Yunping Liu An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index Journal of Marine Science and Engineering underwater image enhancement generative adversarial network natural image quality evaluation index the true image |
| title | An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index |
| title_full | An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index |
| title_fullStr | An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index |
| title_full_unstemmed | An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index |
| title_short | An Underwater Image Enhancement Algorithm Based on Generative Adversarial Network and Natural Image Quality Evaluation Index |
| title_sort | underwater image enhancement algorithm based on generative adversarial network and natural image quality evaluation index |
| topic | underwater image enhancement generative adversarial network natural image quality evaluation index the true image |
| url | https://www.mdpi.com/2077-1312/9/7/691 |
| work_keys_str_mv | AT kaihu anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT yanwenzhang anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT chenghangweng anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT pengshengwang anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT zhiliangdeng anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT yunpingliu anunderwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT kaihu underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT yanwenzhang underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT chenghangweng underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT pengshengwang underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT zhiliangdeng underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex AT yunpingliu underwaterimageenhancementalgorithmbasedongenerativeadversarialnetworkandnaturalimagequalityevaluationindex |