Effective Single Underwater Image Enhancement by Fusion

Due to the absorption and scattering, the clarity and the observation of the depth of field of the image which is obtained by underwater photoelectric imaging will be reduced. This paper introduces a new single image enhancement approach based on image fusion strategy. The method first applies the white balance and global contrast enhancement technologies to the original image respectively, then taking these two adapted versions of the original image as inputs that are weighted by specific maps. We obtain the enhanced results by computing the weight sum of the two inputs in a per-pixel fashion. Since we do not employ deconvolution (computationally expensive), the algorithm reduce the execution time and can effectively enhance the underwater image. The experimental results demonstrate that our method can obtain good visual quality.