基于Gauss-Markov随机场的贝叶斯盲复原

针对图像盲复原中图像细节恢复的同时块效应放大的问题，提出了一种贝叶斯盲复原算法。首先使用贝叶斯框架模式，对原始图像、观察图像、点扩散函数(PSF)及模型参数分别建立先验模型，并将能有效描述图像局部统计特征的带有高斯特性的Markov(Gauss-Markov)随机场模型作为原始图像的先验模型；然后利用贝叶斯公式推导出原始图像及点扩散函数的迭代公式。实验结果表明，与总变分(TV)先验模型的恢复图像相比，所提算法的恢复图像块效应明显减少，并且视觉效果更好；在点扩散函数的大小已知和未知的情况下，相比TV先验模型，所提算法的改善信噪比(ISNR)能提高1dB左右。

Bayesian blind deblurring based on Gauss-Markov random field

A Bayesian blind deblurring algorithm was proposed for solving the contradiction of image details restoration and blocking effect amplification. Based on Bayesian framework, prior models were established for origin image, observed image, point spread function and model parameters. Gauss-Markov random field model that can effectively describe local statistical features of image was introduced as prior model of origin image. Then the iterative formulas of origin image and the point spread function were deduced by using Bayesian formula. The experimental results show that image restorted by the proposed algorithm has fewer blocking effect and better visual effect than the restored image by Total Variation (TV) prior model. Whether the size of point spread function is known or not, compared with TV prior model, the proposed algorithm can increase the Improved Signal to Noise Ratio (ISNR) of the restored image about 1dB.