摘要
介绍了Tikhonov正则化超分辨率重建算法的基本原理和特点,在原有正则化空域图像复原方法的基础上,根据多帧序列图像之间的互补信息,提出一种改进的正则化空域图像复原的新方法,该算法直接将正则化函数作用于图像超分辨率重建算法的条件概率项内,提高了正则化项的校正效率,并用共轭梯度运算来改善算法的收敛性,节省了图像重建所需的时间。实验和仿真结果表明,与传统方法相比,该算法不仅减轻了图像边缘纹理的模糊性,提高了图像的清晰度,而且收敛速度快。
This paper introduced theories and characteristics of the Tikhonov regularized super-resolution reconstruction algorithm.Based on the customary regularization technology and the complementary information of the multiframe image sequences,presented a new method for image restoration.By embedding regularization in similarity term of the super-resolution reconstruction algorithm,improved the rectify efficiency of regularization term,and improved the convergence by conjugate gradient method,saved the time of image restoration.The result of experiment and computer simulations show that the performance of this algorithm is better than the traditional method.It is fast,and reduces fuzzy edge of the images.
出处
《计算机应用研究》
CSCD
北大核心
2011年第2期785-787,791,共4页
Application Research of Computers
基金
河北省教育厅基金资助项目( 2007143)
