Underwater image enhancement through color deviation detection-guided peak flattening

Underwater images frequently exhibit color deviation and blurring. Color deviation arises from the selective spectral absorption of light, whereas blurring results from particle scattering within the water. These challenges impede the performance of high-level visual perception tasks. To improve the underwater image quality, we propose an adaptive method for underwater image enhancement that employs color deviation detection-guided peak flattening. Utilizing six features identified through statistical analysis of the latest underwater real-image datasets, we develop a color deviation detection model for underwater images, which employs ensemble learning to quantify the extent of color deviation. Subsequently, we devise the peak flattening algorithm to achieve histogram adaptive partition conversion. The conversion range is determined by the estimated color deviation value, eliminating the need for iteration. For channels with severe color deviation, we employ the weighted fusion to restore partial gray distribution. Comparisons with state-of-the-art methods demonstrate that the proposed method significantly improves contrast and color fidelity, particularly in images with severe degradation.