Underwater Image Restoration Based on Red Channel and Haze-Lines Prior

Abstract

Due to the scattering and absorption of light while it propagates in the water, underwater images often suffer from low contrast and color distortion. In order to solve this problem, we propose an underwater image restoration algorithm based on red channel and haze-lines prior in this paper. Firstly, the red channel prior is used to estimate veiling-light. Secondly, according to the characteristics of red channel attenuation in water, the attenuation ratio of red-blue channel and red-green channel are introduced to estimate the transmission by using haze-lines prior. Finally, the transmission is corrected by the red channel boundary constraint. In addition, for underwater artificial illumination, we introduce saturation as the low bound of the transmission estimation to reduce the impact of artificial light. The experimental results show that the proposed algorithm can restore image color information, improve image clarity and obtain better visual quality. The quantitative analysis indicates that the proposed algorithm performs well on a wide variety of underwater images and is competitive with other state-of-the-arts.