Restoration and Enhancement of Underwater Under-Exposure Images with Detail-Preserving

Abstract

Underwater images have great practical value in many fields such as underwater archeology, seabed mining, and underwater exploration. Due to the complex underwater environment, there are problems such as poor light, low contrast, and color degradation. Traditional underwater image processing methods cannot well achieve the goal of clear display under extreme conditions. This paper proposes a method for restoration and enhancement of underwater under-exposure images that protects edge details and enhances image color. Firstly, the underwater image was preprocessed, denoising with improved wavelet threshold function, defogging with the Multi-Scale Retinex Color Restoration (MSRCR) and guided filter method. Then, the method of adaptive exposure graph is used to enhance the under-exposure image. Finally, the deep learning algorithm combined with the Non-Subsampled Contour Transform (NSCT) technology is used to solve the problem of color degradation and edge texture weakening. Experiments show that compared with other underwater image processing methods, this method greatly improves the clarity of the image, enhances the color saturation and the edge texture details of the image, and has a better visual effect.