Coordinated underwater dark channel prior for artifact removal of challenging image enhancement

Abstract:

When dehazing underwater images, the patch-by-patch dark channel prior (DCP) method is frequently used. After the DCP-based processing, there are still some drawbacks, such as patch artifacts, and these artifacts will seriously affect the subjective quality of some challenging images. To remove the patch artifacts from the DCP-guided enhancement mechanism, this paper proposes a coordinated underwater dark channel prior (CUDCP) method. The proposed method considers the characteristics of the red-green-blue channels with different attenuation situations, and thus the attenuation ratios of the red-green-blue channels are adaptively coordinated in diverse images. The requirement for color restoration is then assessed by an evaluation criterion, and the color restoration is carried out by using the compensated gray world (CGW) theory, which further coordinates the intensity of various red-green-blue channels. Our method next applies a patch-division average filter in accordance with the sub-patch classification. On the typical dataset, the enhanced images of our CUDCP method have higher average underwater image quality measure (UIQM) scores (about 2.274 8) when compared with the original images and those of some state-of-the-art enhancement methods, while the computational cost of CUDCP (about 88.618 8 s) is slightly higher than that of the original DCP (about 87.493 8 s). The experimental results demonstrate that in comparison to state-of-the-art enhancement methods, the proposed method can significantly reduce patch artifacts in challenging image enhancement, while maintaining the objective quality of such underwater images, and also enhancing their subjective quality at a reasonable computational cost.