Underwater Image Enhancement Based on Improved Haze-lines Prior and Histogram Distribution Prior
Tianshun Chen, Liran Shen, Yunsheng Fan, Chengjie Wang, Chenglong Sun · 2022
In order to solve the low contrast and color shift suffered by underwater images, a hybrid underwater image enhancement method is proposed in this paper. The global attenuation ratio of the underwater image is calculated by using the background light. Based on this, the transmission map of the underwater image is estimated by using haze-lines prior. Then the clear underwater image is recovered from the degraded underwater image. A contrast enhancement method is introduced further to enrich the color and details. The experimental results on different real-world underwater scenes indicate that the proposed method produces visually satisfactory results.