基于全变差的超分辨率图像重建  

Reconstruction of super-resolution image based on variation

作　　者：王艳琴[1] 吴爱弟[1] 王静[1] 

机构地区：[1]天津职业技术师范大学理学院,天津300222

出　　处：《天津职业技术师范大学学报》2014年第2期30-33,共4页Journal of Tianjin University of Technology and Education

基　　金：天津市应用基础及前沿技术研究计划项目(12JCYBJC10600)

摘　　要：根据低分辨率图像生成的矩阵模型,应用广义逆矩阵理论,得到高分辨率图像所在的解空间,把最小总体变差作为目标函数,应用最速下降方法求解,得到重建的高分辨率图像。实验结果表明:该方法能够提高重建图像质量,具有较好的鲁棒性。Based on the matrix model of low resolution image generation and the application of the generalized inverse matrix theory,the solution space is obtained with the the minimum total variation as the objective function,and the steepest descent method is used to obtain high resolution image reconstruction.The experimental results show that： this method can improve the quality of image reconstruction,and has good robustness.

关 键 词：超分辨率图像 广义逆 全变差 正则化 迭代 梯度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]