Abstract: Motion blur is one of common blurs that degrades images.Restoration of images is highly dependent on estimation of motion blur parameters.The authors have presented a novel algorithm to estimate linear motion blur parameters such as direction and extend by using radon transform to find direction and fuzzy set concepts to find its extend.This method has heen tested on a wide range of different type of standard images that had been degraded.This algorithm’s robustness and precision in noisy images is improved greatly.Though SNR is rather low,we still get highly satisfactory result.

Key words: blur extend, fuzzy set, robustness, Radon transform

摘要： 运动模糊是降质图像中常见的一种形式,运动模糊图像的恢复主要依靠对运动模糊参数的估计。提出了一种新的算法来估计线性运动模糊参数。该算法利用Radon变换找到运动模糊图像的方向,通过运用模糊理论中的t-norm调整得到模糊尺度。实验结果表明,该算法在鲁棒性和精确性上均有很大提高且即使在信噪比比较低的情况下仍然可以得到很好的恢复效果。

关键词: 模糊尺度, 模糊集, 鲁棒性, Radon变换