Underwater image restoration based on channel compensation and dark channel prior

Abstract

Due to the absorption and scattering of light by water medium and suspended particles, underwater images come with color deviation and blurred details. For different light absorption in different underwater environments, an adaptive compensation method for local color channels is proposed to enhance the compensation for severe attenuation areas, which is suitable for underwater scenes with multiple color deviations. The dark channel prior is used to remove the detail blurring caused by scattering, the multi-scale Gaussian convolution and gamma correction are adopted to estimate the local light, and the tolerance parameter is used to increase the transmittance of bright areas to compensate for the dark channel prior conditions. The enhanced image quality is evaluated by Underwater Image Quality Measurement (UIQM), Average Gradient (AG), and entropy. Experimental data show that the method improves the color deviation of underwater images in different environments, enhances color information, and improves the contrast of images.