Underwater Image Restoration Based on Improved Background Light Estimation and Automatic White Balance

摘要

A new algorithm for underwater image restoration based on improved background light estimation and automatic white balance is proposed in order to overcome the shortage of classical dark channel prior algorithm for underwater image restoration. The improved background light estimation method can reduce the influence of light and white objects in the water and improve the accuracy of the background light. The improved automatic white balance algorithm can reduce the color distortion and get a clear image with the color correction of the restored image. According to the contrast experiments of four different underwater images, we can see that the algorithm has some advantages on subjective and objective evaluation indexes, and the sharpness and the color fidelity of the enhanced image are better.