An adaptive color correction method for underwater single image haze removal

The issue of underwater image haze removal is investigated in this paper. The exponential attenuation phenomenon in the underwater light propagation process causes the low contrast, color distortion, and blurred edges problems of underwater images and consequently limits the application of the vision-based underwater technology. To overcome these problems, an adaptive color correction method is proposed for underwater single image haze removal. First of all, the estimated transmission map by image blurriness is adopted in the image formation model to remove the haze of underwater images. Secondly, the alternating direction method of multipliers and the histogram displacement in the Lab color space are used to improve the uniform brightness and to correct the color distortion of the restored underwater images. Finally, both qualitative and quantitative experimental results show that the proposed method can produce better restoration results in different underwater scenes compared to other state-of-the-art underwater image restoration methods.