您的位置：首页 > 论文页面
盲图像恢复的两个关键问题研究
发表时间：2017-02-28 浏览量：1607 下载量：602
| 全部作者： | 黄丽清，夏又生 |
| 作者单位： | 福州大学数学与计算机科学学院 |
| 摘 要： | 有效估计模糊核尺寸和识别模糊核类型是盲图像恢复的两个关键问题。为解决这两个关键问题，首次提出一种基于特征线检测的模糊核尺寸估计算法及一种基于字典学习的模糊核类型识别算法。特征线检测主要包括图像对数归一化特征、二值转化及特征线统计规则。字典学习包括观测图像的结构相似性指标、训练库图像的相似性指标及判定结构最相似的类型图。实验结果证实所提出的两种算法能有效估计模糊核尺寸和识别模糊核类型。最后，应用结果进一步显示所提出的两种算法对提高盲图像恢复效果起到重要作用。 |
| 关 键 词： | 信息处理技术；盲图像恢复；模糊核尺寸估计；模糊类型识别；参数化模型 |
| Title： | Study of two key problems of blind image restoration |
| Author： | HUANG Liqing, XIA Yousheng |
| Organization： | College of Mathematics and Computer Science, Fuzhou University |
| Abstract： | Effectively estimating the size of blur kernel and identifying its type are two key issues of blind image restoration. In order to solve them, a feature line detection-based algorithm for estimating the size of blur kernel and a dictionary learning-based algorithm for identifying the type of blur kernel are proposed in this paper for the first time, respectively. The feature line detection mainly includes logarithmic normalized feature matrix of blurred images, binary transform of feature matrix, and feature line statistical rules. Dictionary learning includes logarithmic normalized feature matrix of observed images and training library images, the calculation of structural similarity index, determining the best structural similarity between observed images and dictionary images. Experimental results show that the two proposed algorithms are very effective. Furthermore, an application to blind image restoration shows that the two proposed algorithms are useful and necessary. |
| Key words： | information processing technology; blind image restoration; blur kernel size estimation; blur type identification; parameterized model |
| 发表期数： | 2017年2月第4期 |
| 引用格式： | 黄丽清，夏又生. 盲图像恢复的两个关键问题研究[J]. 中国科技论文在线精品论文，2017，10（4）：454-470. |
3
评论数 0请您登录
暂无评论
下载全文
多维论文