Radon变换和全变分相融合的图像复原算法

图像复原的核心是点扩散函数的估计和直接去卷积算法,针对拍照过程中,相机和被拍摄物体由于相对运动而导致的图像退化问题,提出一种基于Radon变换和全变分相融合的图像复原算法。首先利用radon变换对图像退化模型参数进行估计,然后采用全变分算法复原退化图像,最后在Matlab 2012平台进行仿真实验对算法的性能检验。仿真结果表明,相对于其它图像复原算法,本文算法可以准确估计退化模型参数,获得了更加理想的图像复原效果,具有一定的实际利用价值。

Image restoration algorithm based on radon transform and total variation

The point spread function and non blind de-convolution algorithm is the key of the blurred image blind restoration. For the problem of motion-blur by the relative motion between the camera and the object during taking pictures, in order to obtain good restoration results, a novel image restoration algorithm is proposed based on radon transform and total variation in this paper. Firstly, the motion blur parameters of point spread function are estimated based on radon transform, and then the motion blur image is restored based on total variation, finally the simulation experiments are carried out to test the performance of algorithm. The results show that the proposed algorithm can estimate the motion blur parameters, obtain better restoration affects compared with other image restoration algorithms, so it has a certain application value.