张量投票在图像修复中的应用  

Application of Tensor Voting in Image Inpainting

作　　者：邵晓芳[1] 初晓军[1] 

机构地区：[1]海军航空工程学院青岛校区,山东青岛

出　　处：《图像与信号处理》2017年第1期1-7,共7页Journal of Image and Signal Processing

摘　　要：图像修复技术是计算机图形学和机器视觉中的研究热点之一,在文物保护、多余目标物体剔除、影视特技制作、图像缩放、图像的有损压缩、视频通信的错误隐匿等方面均有重大应用价值。在分类总结相关工作的基础上,介绍了张量投票方法在图像修复中的应用,并展示了该方法的实验处理效果。Image inpainting is one of research hotspots both in computer graphics and computer vision, which can be applied in historic preservation, unwanted objects elimination, film and television special effects production, image resizing, image compression and error concealment of video communication. This paper presents a summary of related works and introduces how to apply the tensor voting method in optical pre-processing. The algorithm’s flowchart and typical experimental result are demonstrated to show the completion characteristics of the algorithm.

关 键 词：图像修复 自适应尺度 张量投票 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]