Underwater image enhancement method via extreme enhancement and ultimate weakening

Abstract

The existing histogram-based methods for underwater image enhancement are prone to over-enhancement, which will affect the analysis of enhanced images. However, an idea that achieves contrast balance by enhancing and weakening the contrast of an image can address the problem. Therefore, an underwater image enhancement method based on extreme enhancement and ultimate weakening (EEUW) is proposed in this paper. This approach comprises two main steps. Firstly, an image with extreme contrast can be achieved by applying grey prediction evolution algorithm (GPE), which is the first time that GPE is introduced into dual-histogram thresholding method to find the optimal segmentation threshold for accurate segmentation. Secondly, a pure gray image can be obtained through a fusion strategy based on the grayscale world assumption to achieve the ultimate weakening. Experiments conducted on three standard underwater image benchmark datasets validate that EEUW outperforms the 10 state-of-the-art methods in improving the contrast of underwater images.