Underwater Image Enhancement Based on Multiscale Fusion

Abstract

To improve the visibility and clarity of images in underwater environment, this paper proposes an underwater image enhancement method based on multi-scale fusion. Firstly, the white balance method is used to correct the color of the underwater image, and the original color of the underwater elements is restored as much as possible. Secondly, the dark channel prior algorithm is used to solve the underwater image blur problem. Then, the CLAHE algorithm is used to enhance the contrast of the image. Finally, using weight allocation or fusion rules, multi-scale information and multi-stage fusion of the image are used to generate the final enhanced underwater image. Quantitative image quality evaluation indexes PSNR, SSIM and UIQE are used to evaluate underwater image quality. The results show that the proposed method can effectively solve the problem of underwater image color deviation, make the color of the image more accurate and natural, improve the contrast and brightness of the underwater image, and have better visual effect and richer detail information.