作者: Jian-Feng Cai , Hui Ji , Chaoqiang Liu , Zuowei Shen
关键词: Deblurring 、 Motion blur 、 Computer vision 、 Bregman method 、 Real image 、 Digital imaging 、 Mathematics 、 Pattern recognition 、 Image processing 、 Kernel (image processing) 、 Image restoration 、 Artificial intelligence
摘要: How to recover a clear image from single motion-blurred has long been challenging open problem in digital imaging. In this paper, we focus on how due camera shake. A regularization-based approach is proposed remove motion blurring the by regularizing sparsity of both original and motion-blur kernel under tight wavelet frame systems. Furthermore, an adapted version split Bregman method efficiently solve resulting minimization problem. The experiments synthesized images real show that our algorithm can effectively complex natural without requiring any prior information kernel.