Underwater image enhancement based on zero-shot learning and level adjustment
Light is scattered and partially absorbed while traveling through water, hence, underwater captured images often exhibit issues such as low contrast, detail blurring, color attenuation, and low illumination. To improve the visual performance of underwater imaging, herein, we propose a two-step metho...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023016493 |
| _version_ | 1797837100840648704 |
|---|---|
| author | Qiang Xie Xiujing Gao Zhen Liu Hongwu Huang |
| author_facet | Qiang Xie Xiujing Gao Zhen Liu Hongwu Huang |
| author_sort | Qiang Xie |
| collection | DOAJ |
| description | Light is scattered and partially absorbed while traveling through water, hence, underwater captured images often exhibit issues such as low contrast, detail blurring, color attenuation, and low illumination. To improve the visual performance of underwater imaging, herein, we propose a two-step method of zero-shot dehazing and level adjustment. In the newly developed approach, the original image is fed into a “zero-shot” dehazing network and further enhanced by an improved level adjustment methodology combined with auto-contrast. By conducting experiments, we then compare the performance of the proposed method with six classical state-of-the-art methods. The qualitative results confirm that the proposed method is capable of effectively removing haze, correcting color deviations, and maintaining the naturalness of images. We further perform a quantitative evaluation, revealing that the proposed method outperforms the comparison methods in terms of peak signal-to-noise ratio and structural similarity. The enhancement results are also measured by employing the underwater color image quality evaluation index (UCIQE), indicating that the proposed approach exhibits the highest mean values of 0.58 and 0.53 on the two data sets. The experimental results collectively validate the efficiency of the proposed methodology in enhancing underwater blurred images. |
| first_indexed | 2024-04-09T15:19:23Z |
| format | Article |
| id | doaj.art-7cb5479f5ce145f78153d710484bb5fd |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-09T15:19:23Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-7cb5479f5ce145f78153d710484bb5fd2023-04-29T14:50:17ZengElsevierHeliyon2405-84402023-04-0194e14442Underwater image enhancement based on zero-shot learning and level adjustmentQiang Xie0Xiujing Gao1Zhen Liu2Hongwu Huang3School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, Fujian 361024 China; Corresponding author.Institute of Smart Marine and Engineering, Fujian University of Technology, Fuzhou, Fujian 350118, China; Corresponding author.School of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, Fujian 361024 ChinaSchool of Mechanical and Automotive Engineering, Xiamen University of Technology, Xiamen, Fujian 361024 China; Institute of Smart Marine and Engineering, Fujian University of Technology, Fuzhou, Fujian 350118, ChinaLight is scattered and partially absorbed while traveling through water, hence, underwater captured images often exhibit issues such as low contrast, detail blurring, color attenuation, and low illumination. To improve the visual performance of underwater imaging, herein, we propose a two-step method of zero-shot dehazing and level adjustment. In the newly developed approach, the original image is fed into a “zero-shot” dehazing network and further enhanced by an improved level adjustment methodology combined with auto-contrast. By conducting experiments, we then compare the performance of the proposed method with six classical state-of-the-art methods. The qualitative results confirm that the proposed method is capable of effectively removing haze, correcting color deviations, and maintaining the naturalness of images. We further perform a quantitative evaluation, revealing that the proposed method outperforms the comparison methods in terms of peak signal-to-noise ratio and structural similarity. The enhancement results are also measured by employing the underwater color image quality evaluation index (UCIQE), indicating that the proposed approach exhibits the highest mean values of 0.58 and 0.53 on the two data sets. The experimental results collectively validate the efficiency of the proposed methodology in enhancing underwater blurred images.http://www.sciencedirect.com/science/article/pii/S2405844023016493Underwater image enhancementImage dehazingUnsupervised learningColor correction |
| spellingShingle | Qiang Xie Xiujing Gao Zhen Liu Hongwu Huang Underwater image enhancement based on zero-shot learning and level adjustment Heliyon Underwater image enhancement Image dehazing Unsupervised learning Color correction |
| title | Underwater image enhancement based on zero-shot learning and level adjustment |
| title_full | Underwater image enhancement based on zero-shot learning and level adjustment |
| title_fullStr | Underwater image enhancement based on zero-shot learning and level adjustment |
| title_full_unstemmed | Underwater image enhancement based on zero-shot learning and level adjustment |
| title_short | Underwater image enhancement based on zero-shot learning and level adjustment |
| title_sort | underwater image enhancement based on zero shot learning and level adjustment |
| topic | Underwater image enhancement Image dehazing Unsupervised learning Color correction |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023016493 |
| work_keys_str_mv | AT qiangxie underwaterimageenhancementbasedonzeroshotlearningandleveladjustment AT xiujinggao underwaterimageenhancementbasedonzeroshotlearningandleveladjustment AT zhenliu underwaterimageenhancementbasedonzeroshotlearningandleveladjustment AT hongwuhuang underwaterimageenhancementbasedonzeroshotlearningandleveladjustment |