Motion Deblurring from a Single Photograph based on Kernel Estimation

In this paper, we propose a simple and efficient motion deblurring method based on fast kernel retrieval method, which can quickly find the best kernel from a set of kernels. Owing to camera shake during exposure, it may generate a motion blurred image; this kind of blur is often nonlinear motion and caused the deterioration. For this reason, reconstructing a blurred image into a sharp image is the main objective in this paper. Reconstruction a motion blur image is an ill-posed problem. Many state-of-the-art methods for motion blur estimation usually use the recursive method to estimate motion blur kernel. However, recursive process is quite time-consuming. In order to reduce the execution time, in this paper, based on iterative phase retrieval algorithm and normalized sparsity measure, we propose a fast blur kernel retrieval algorithm to quickly obtain the best kernel and to achieve the deblurring. The results demonstrate that this method can effectively speed up the execution time and give the best motion blur kernel and maintain the good image deblurring quality.