Underwater Image Enhancement Based on Global Dual Gamma Correction Combined with WOA Algorithm
Ying Wang, Zijun Gao, Nan Wang · 2024
Due to light absorption and scattering, underwater images often suffer from quality degradation problems such as color deviation, low contrast, and blurred details. To address these problems, we propose a low-light image enhancement method based on the combination of global dual gamma correction and Whale Optimization Algorithm(WOA). Firstly, we use the double gamma function to correct the image globally with the WOA algorithm, in addition, we optimize the selection of the parameter $(\alpha)$ to improve the convergence performance of the algorithm, so as to find the optimal gamma value to achieve the details of the image enhancement, and finally, we put in the U-Net network with the added attention to further optimize the image enhancement. The experimental results show that the overall underwater enhancement effect of this paper is better than other comparative algorithms, and the evaluation indexes PNSR, SSIM, and UIQM achieve the highest values of 33.01, 0.974, and 3.042, respectively.