Region-specialized underwater image restoration in inhomogeneous optical environments

Underwater optical imaging and image processing play an important role in oceanic scientific research and practical applications. However, as light is absorbed and scattered by the water which it passes through, the underwater image acquired is seriously degraded. The resolution and contrast are lowered by light scattering and color is distorted by the wavelength-selective absorption. In order to solve these problems, various artificial sources are widely used in underwater imaging systems. However, additional sources except the parallel background light will cause pollution to the underwater optical environments, making it inhomogeneous. In this condition, the popular image processing methods based on the assumption of the homogeneous ambient light are weak or even futile. Aimed to solve this problem, a region-specialized method for underwater image restoration is proposed in this paper. Region-varied changes in the ambient light are taken into consideration for dehazing and color compensation. In contrast to the references including the state of art methods for both underwater image enhancement and restoration, the enhanced clarity and color fidelity are obtained through visual evaluation. Moreover, the highest score of no-reference perceptual quality assessment is obtained by the proposed method as well.