Version 1
: Received: 18 July 2024 / Approved: 19 July 2024 / Online: 19 July 2024 (06:40:56 CEST)
How to cite:
Liu, X.; Chen, Z.; Xu, Z.; Zheng, Z.; Ma, F.; Wang, Y. Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN. Preprints2024, 2024071575. https://doi.org/10.20944/preprints202407.1575.v1
Liu, X.; Chen, Z.; Xu, Z.; Zheng, Z.; Ma, F.; Wang, Y. Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN. Preprints 2024, 2024071575. https://doi.org/10.20944/preprints202407.1575.v1
Liu, X.; Chen, Z.; Xu, Z.; Zheng, Z.; Ma, F.; Wang, Y. Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN. Preprints2024, 2024071575. https://doi.org/10.20944/preprints202407.1575.v1
APA Style
Liu, X., Chen, Z., Xu, Z., Zheng, Z., Ma, F., & Wang, Y. (2024). Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN. Preprints. https://doi.org/10.20944/preprints202407.1575.v1
Chicago/Turabian Style
Liu, X., Fengshuang Ma and Yunjie Wang. 2024 "Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN" Preprints. https://doi.org/10.20944/preprints202407.1575.v1
Abstract
Ocean exploration is crucial for utilizing its extensive resources. Images captured by underwater robots suffer from issues such as color distortion and reduced contrast. To address the issue, we propose an innovative enhancement algorithm that integrates Transformer and Convolutional Neural Network (CNN) in a parallel fusion manner. Firstly, a novel transformer model is intro-duced to capture local features, employing peak-signal-to-noise ratio (PSNR) attention and linear operations. Subsequently, to extract global features, both temporal and frequency domain features are incorporated to construct convolutional neural network. Finally, the Fourier’s high and low-frequency information of the original image are utilized to fuse different features. To demon-strate the algorithm's effectiveness, underwater images with various levels of color distortion are selected for both qualitative and quantitative analyses. The experimental results demonstrate that our approach surpasses other mainstream methods, achieving superior PSNR and structural sim-ilarity index measure (SSIM) metrics and leading to a detection performance improvement of over ten percent.
Keywords
image enhancement; local features; global features; parallel fusion
Subject
Computer Science and Mathematics, Robotics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.