| 采用自适应正则参数的超分辨率加权重建 |
| |
| 引用本文： | 陈大伟,胡访宇.采用自适应正则参数的超分辨率加权重建[J].无线电工程,2011,41(5):18-19,61. |
| |
| 作者姓名： | 陈大伟 胡访宇 |
| |
| 作者单位： | 中国科学技术大学,安徽,合肥,230027 |
| |
| 摘 要： | 采用L1(一阶)、L2(二阶)范数是当前较为流行的2种图像超分辨率重建算法。在对这2种算法的优缺点进行分析的基础上,提出了一种采用L1和L2范数混合加权的参数自适应双边全变差正则化重建算法,将正则化参数作为重建图像的一个函数。实验证明这种算法有很好的边缘保持和去除椒盐噪声的能力,重建图像的质量有显著提高。
|
| 关 键 词： | 超分辨率 L1、L2范数 自适应正则化 双边全变差 |
A Weighted Super Resolution Reconstruction Method Adopting Adaptive Regularization Parameter |
| |
| CHEN Da-wei,HU Fang-yu.A Weighted Super Resolution Reconstruction Method Adopting Adaptive Regularization Parameter[J].Radio Engineering of China,2011,41(5):18-19,61. |
| |
| Authors: | CHEN Da-wei HU Fang-yu |
| |
| Affiliation: | CHEN Da-wei,HU Fang-yu(University of Science and Technology of China,Hefei Anhui 230027,China) |
| |
| Abstract: | The algorithms that adopts L1 and L2 norm minimization estimator are the most popular algorithms of super-resolution reconstruction.Thus in this paper,The two algorithms are combined based on analysis of the pros and cons of them,then a bilateral total variation regularization method is adopted and a weighted super resolution reconstruction algorithm is proposed based on an adaptive regularization parameter.The adaptive method regards the regularization parameter as a function of the restored image.Experime... |
| |
| Keywords: | super-resolution L1-norm L2-norm adaptive regularization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
