Enhancement of underwater images through a dehazing approach with color balancing and multiscale image fusion

Abstract

Underwater environment is potentially rich for scientific research and explorations, but it is challenging to capture the image of the underwater environment due to light absorption and scattering effects of water. In this research, white balance algorithm is employed to recover the lost color information and multiscale image fusion is applied to the features of gamma corrected and sharpened image for dehazing the underwater image and improve the contrast. This paper proposes an approach that enhances color correction with Histogram Equalization and applies Contrast Limited Adaptive Histogram Equalization to sharpened image to further improve the details of the underwater image. The UIEB and two widely used underwater image datasets are used which include underwater scenery with fish, coral reefs, divers, underwater structures and shipwrecks. The application of the multiscale image fusion with proposed algorithm achieves to balance the distorted colors of underwater image and enhances fine details and contrast to improve image quality. Comparison of the proposed method with the state-of-the-art based on eight performance metrics demonstrates that the proposed method results are encouraging and comparable with the state-of-the-art.