Blurred Image Restoration Using Fast Blur-Kernel Estimation

Motion blur is usually generated when people captured a picture in the daily life. This kind of blur is often non-liner motion and may cause the blurred contents seriously in this image. Hence, how to remove the blurred image into a clear image becomes a very important scheme. In this paper, the primary aim is to propose an efficient blurred image restoration method based on fast blur-kernel estimation, which can quickly find the best kernel from a set of kernels. Many state-of-the-art methods for motion blur estimation usually use the recursive method to estimate motion blur kernel. However, it is quite time-consuming. In order to reduce the computational time, we use iterative phase retrieval algorithm and normalized sparsity measure to quickly obtain the best kernel and to achieve the deblurring. Experimental results verify that this approach can effectively speed up the executing time and obtain the best motion blur kernel and maintain the high quality of image deblurring.