|
|||||
|
|
| 基于图像分解的敦煌壁画图像修复方法 | |
| 引用本文： | 黄伟,王书文,杨筱平,贾建芳.基于图像分解的敦煌壁画图像修复方法[J].山东大学学报(工学版),2010,40(2):24-27. |
| 作者姓名： | 黄伟 王书文 杨筱平 贾建芳 |
| 作者单位： | 1. 周口师范学院计算机科学系, 河南 周口 466001; 2. 西北民族大学电气工程学院, 甘肃 兰州 730030; 3. 西北民族大学中国民族信息技术研究院, 甘肃 兰州 730030 |
| 基金项目： | 国家自然科学基金，甘肃省科技攻关项目 |
| 摘 要： | 提出一种基于分解的图像修复算法,该算法对敦煌壁画的数字图像进行修复。选择用Lαβ色彩空间进行通道分解实现彩色图像的修复,并利用整体变分降噪模型进行图像分解,该分解算法不需要进行Banach空间范数的计算,不仅降低模型的数值计算复杂度,还可以降低敦煌壁画中的噪声对修复结果的影响。实验证明:该算法很好地解决壁画中的划痕和脱落等现象的破损,修复效果较好。 |
| 关 键 词： | 图像修复 图像分解 结构 纹理 L&alpha &beta 色彩空间 |
| 收稿时间： | 2009-05-25 |
Dunhuang murals in-painting based on image decomposition |
|
| HUANG Wei,WANG Shu-wen,YANG Xiao-ping,JIA Jian-fang.Dunhuang murals in-painting based on image decomposition[J].Journal of Shandong University of Technology,2010,40(2):24-27. | |
| Authors: | HUANG Wei WANG Shu-wen YANG Xiao-ping JIA Jian-fang |
| Affiliation: | 1. Department of Computer Science, Zhoukou Normal University, Zhoukou 466001, China; 2. College of Electrical Engineering, Northwest University for Nationalities, Lanzhou 730030, China; 3. China Minorities Information Technology Institute, Northwest University for Nationalities, Lanzhou 730030, China |
| Abstract: | An algorithm for image in-painting based on decomposition was proposed to in-paint the digital images of Dunhuang murals. The color image in-painting was achieved by using the Lαβ color space for the access decomposition and by using the total variation(TV) noise model for image decomposition. The decomposition algorithm did not require the calculation of Banach space norm. This method could not only reduce the complexity of the numerical calculation of the model, but also reduce the affection that noise made on the results of repair in Dunhuang murals. The experiments showed that this algorithm could well in-paint the shedding and scratch of the damaged Dunhuang murals. |
| Keywords: | image in-painting image decomposition structure texture |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《山东大学学报(工学版)》浏览原始摘要信息 | |
| 点击此处可从《山东大学学报(工学版)》下载全文 | |