基于指数律分布的图像快速盲复原算法

Fast Blind Image Restoration Algorithm Based on Power Law

针对现有图像盲复原迭代算法多存在耗时较长和难以保证收敛性等问题,提出一种改进的快速算法.首先根据指数律重建原始图像的频谱,然后利用原始图像和降质图像的频谱关系,采用多方向综合估计方法得到点扩散函数.多方向综合估计方法可降低估计误差,增加算法的稳定性.最后利用得到的点扩散函数和维纳滤波法进行图像重建.与现有算法的对比实验结果表明,针对适合大量成像系统的G类点扩散函数,本算法可以得到更准确的点扩散函数估计,且降低了振铃效应的影响,取得更好的图像复原效果.

Aiming at the problems that the existing iterative blind image restoration algorithms are mostly time-consuming and their convergence guaranteeing is difficult, a fast algorithm was proposed. Firstly, the spectrum of original image is reconstructed in accordance with the power law. Then, utilizing the relationship between the spectrums of the orignal and reconstructed images, the Point Spread Function （PSF） is estimated by the multidirectional comprehensive estimation, which can reduce the estimation error and enhance the stablility. Finnaly, the restored image is obtained by using the estimated PSF and Wiener filter. The proposed algorithm was compared with the existing algorithms by experiments. The results show that for the class G PSFs which fit for the numerous imaging systems, the proposed algorithm can obtain more accurate PSF, and reduce the ringing artifacts, yielding restored images with higher quality.