Abstract
In either situation, underwater vision is affected by low light, diffraction, and color aberrations that lead to image distortion. To prevent this, we implemented a Texture Distribution Mapping Approach for undersea image improvement using MATLAB. Under this framework, we will enhance texture distribution, contrast, and visibility in general by controlling the most relevant properties of texture in the underwater environment. The TDM process is incremental: it involves pre-processing to eliminate noise and color distortion, followed by enhancement using another method for texture improvement. By enhancing texture mapping onto the image, we achieve a balance of visibility in high-texture regions, resulting in low-texture regions and better clarity and coloring. The method was compared against real underwater image data sets and tested for performance using quality measures like UCIQE (Underwater Color Image Quality Evaluation) and UIQM (Underwater Image Quality Measure). Experimental results and MATLAB implementation of the proposed algorithm exhibited stunning improvements in image quality and luminosity enhancements in texture compared to baseline methods, especially in challenging water conditions.
References
- Li, Chengda, Xiang Dong, Yu Wang, and Shuo Wang. "Enhancement and optimization of underwater images and videos mapping." Sensors 23, no. 12 (2023): 5708.
- Zhou, Wen-Hui, Deng-Ming Zhu, Min Shi, Zhao-Xin Li, Ming Duan, Zhao-Qi Wang, Guo-Liang Zhao, and Cheng-Dong Zheng. "Deep images enhancement for turbid underwater images based on unsupervised learning." Computers and Electronics in Agriculture 202 (2022): 107372.
- Raveendran, Smitha, Mukesh D. Patil, and Gajanan K. Birajdar. "Underwater image enhancement: a comprehensive review, recent trends, challenges and applications." Artificial Intelligence Review 54, no. 7 (2021): 5413-5467.
- Lin, Sen, Kaichen Chi, Tong Wei, and Zhiyong Tao. "Underwater image sharpening based on structure restoration and texture enhancement." Applied Optics 60, no. 15 (2021): 4443-4454.
- Zhou, Jingchun, Shiyin Wang, Zifan Lin, Qiuping Jiang, and Ferdous Sohel. "A pixel distribution remapping and multi-prior retinex variational model for underwater image enhancement." IEEE Transactions on Multimedia 26 (2024): 7838-7849.
- Zhang, Weidong, Yudong Wang, and Chongyi Li. "Underwater image enhancement by attenuated color channel correction and detail preserved contrast enhancement." IEEE Journal of Oceanic Engineering 47, no. 3 (2022): 718-735.
- Hu, Shuteng, Zheng Cheng, Guodong Fan, Min Gan, and CL Philip Chen. "Texture-aware and color-consistent learning for underwater image enhancement." Journal of Visual Communication and Image Representation 98 (2024): 104051.
- Wang, Yang, Yang Cao, Jing Zhang, Feng Wu, and Zheng-Jun Zha. "Leveraging deep statistics for underwater image enhancement." ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17, no. 3s (2021): 1-20.
- Liang, Zheng, Weidong Zhang, Rui Ruan, Peixian Zhuang, Xiwang Xie, and Chongyi Li. "Underwater image quality improvement via color, detail, and contrast restoration." IEEE Transactions on Circuits and Systems for Video Technology 34, no. 3 (2023): 1726-1742.
- Tian, Yuan, Yuang Xu, and Jun Zhou. "Underwater image enhancement method based on feature fusion neural network." IEEE Access 10 (2022): 107536-107548.
