Underwater image enhancement based on fusion algorithm

• 1、Electronic and Information Engineering School, Liaoning Technical University, Huludao 125000

Abstract：Underwater optical images are deeply affected by light absorption and scattering. There are many problems in underwater optical images, such as noise interference, blurred texture features, illumination spot, low contrast and color distortion. In order to enhance the quality of underwater image and make it more visible, an underwater image enhancement algorithm based on fusion is proposed in this paper. The aim of this algorithm is to improve the visual effect of underwater images by using the information presented in underwater images to show more visible details and highlight effective information. The algorithm is based on the fusion of three images. Firstly, the degraded image is defogged by the improved DCP algorithm. For the defogged image, CLAHE algorithm and AGCWD algorithm are used to obtain the color correction image and contrast enhancement image respectively. Secondly, the fusion image and its associated weight map are defined, and the enhanced underwater image is obtained by multi-scale fusion method.Finally, the enhanced underwater image is tested and evaluated extensively. Through testing and evaluation, the method can effectively enhance the quality of underwater image. After processing, the image contrast is enhanced, the color is bright, the overall and local details of the image are clear, and the light and dark areas are evenly distributed. The method can greatly improve the visual effect of the image and is suitable for different types of underwater degraded images.

Keywords： Image processing Underwater image enhancement Multi-scale fusion Color correction