Perceptual Uniform Simulation for Tang Tomb Mural Inapinting by Camera Array
发布时间：2024-08-09
点击次数：
- 所属单位：
- 信息与控制工程学院
- 发表刊物：
- International Journal of Simulation: Systems, Science and Technology
- 关键字：
- 中文关键字：图像修复；壁画；相机阵列；优先值，英文关键字：Inpainting； Mural;camera array; priority
- 摘要：
- Image inpainting is an effective restoration technology for damaged images used to fill the lost or deteriorated parts of art treasures. Tang tomb mural uses camera array to get high resolution digital images. It is colorful and has plenty of construction information, so it is hard to make a perceptual uniform simulation. In order to simulate the process of filling the damaged pixels as the restorers do, this paper studies an exemplar based inpainting technique. There are some difficulties to inpaint directly: i) the original exemplar-based image inpainting algorithm relied on a global traversal of all pixels to find the best matching exemplar, it is a big time wasting process; ii) the source of the exemplar using only a single lens capturing image, there is a limit on the exemplars to get the final best effects; iii) the mural is colorful, but the previous algorithm always used RGB color model to inpaint the missing patch individually in three channels which experimentally can easily make a mistake in color display. To solve these problems, in this paper the exemplars source are chosen from camera array, and reduce redundancy aim to save processing time. In order to simulate a visual perceptual uniform process, it takes the mural’s color information into account by adding Lab color parameter to the data term. This helps to calculate the priority value and change the order of the filling strategy. The simulation result shows that the improved algorithm can quickly restore the Tang tomb mural better and reduce the error accumulation.
- 备注：
- 吴萌
- 合写作者：
- 杨文宗
- 第一作者：
- 王慧琴,吴萌
- 论文类型：
- 期刊论文
- 卷号：
- 卷：17
- 期号：
- 期：47
- 页面范围：
- 页：5.1-5.7
- 是否译文：
- 否
- 发表时间：
- 2016-11-01