Underwater image enhancement based on improved adaptive MSRCR and Gamma function
Lin Zhang, Tong Peng · 2023
In order to solve the problem that light is absorbed by different scales and scattered by particles in water, resulting in overall color deviation, low contrast and unclear details of the image, an underwater image enhancement algorithm based on improved adaptive MSRCR(Multi-Scale Retinex with Color Restoration) and two-dimensional gamma function based on details is proposed. Firstly, the weight of the convolution function in different scales is redistributed according to the image gradient information as the selection factor, and then the guided filter and gaussian filter are used as the adaptive MSRCR surround function and linear fusion to solve the problems of color decay and insufficient sharpness. Finally, the improved two-dimensional gamma function with CLAHE(Contrast Limited Adaptive Histogram Equalization) algorithm is used to correct the image contrast after fusion. The experimental results show that the enhanced image processed by this method has good enhancement effect in underwater image elimination of color distortion, image detail enhancement and obtaining real and natural restored image, and has obvious advantages over other contrast algorithms.