Application of blind deconvolution approach with image quality metric in underwater image restoration

The degradation of underwater image obtained by range gated pulsed laser imaging system is mainly caused by scattering and absorption of in-water particles. Although the use of blind deconvolution of image restoration is a widely known concept, little literatures have discussed in detail its application in the problem of restoration of underwater images. In order to extend the imaging distance, we use blind deconvolution approach together with Wells' small angle approximation theory to restore the underwater image to a better level. Due to underwater no-reference imaging environment, image quality judgment based on blur metric method is incorporated in our approach to determine the appropriate deconvolution iteration time, which objectively evaluate the image restoration result.