基于图像频谱全局均值标准差分割的点扩散函数估计

Algorithm of global mean and standard deviation for motion blur parameters identification

实现运动模糊图像恢复的关键是获得准确的点扩散函数(point spread function,PSF)。针对PSF的模糊尺度和模糊方向这两个重要参数,提出了一种基于图像频谱全局均值标准差的估计方法。通过研究运动模糊图像的产生机理,分析了二次傅里叶变换的频谱特性,利用全局均值标准差法对频谱图进行阈值分割,结合中心点和端点的坐标距离来估计模糊尺度,运用Radon变换鉴别模糊方向,实现了PSF参数的确定。进行了标准图像阈值分割准确度的验证,利用仿真模糊图像估计算法进行了验证,并进行了实际复原实验。结果表明,该方法具有误差小、稳定性高和不受运动方向限制的特点,为图像恢复提供了一种准确、简便的参数估计方法。

The estimation of parameters for motion blurred images is dealed with. The objectives are to estimate the length and the blur angle of the given degraded image as accurately as possible so that the restoration performance can be optimized. An algorithm of global mean and standard deviation for motion blur parameters identification is proposed. Radon transform is utilized to estimate the blur angle where as a trained the pixel coordinates estimates the blur length. Once these parameters are estimated the conventional restoration is performed. To validate the proposed scheme, simula- tion has been carried out on standard images as well as in real images subjected to different blur lengths. In all situations, the results have been compared with standard schemes. It is in general observed that the proposed scheme out performs its counterparts in terms of restoration parameters and visual quality.