数据采集与处理2012，Vol.27Issue(4)：444-449,6.
基于Surfacelet稀疏重构的视频修复
Video Inpainting Based on Sparse Reconstruction of Surfacelet
摘要
Abstract
To improve the inpainting quality of the damaged videos with vertical line, scratch and broken characters, a video inpainting algorithm is proposed based on the sparse reconstruction of Surfacelet. Since it has three-dimensional sparse characteristics of multi-scales, multi-directions and efficient tree structure, the singular surface of a video can be effectively captured by the Surfacelet transform. In the proposed algorithm, the objective function of the original video for global optimization is constructed based on Surfacelet transform and solved using the relaxation algorithm to achieve the video inpainting. The proposed algorithm does not need complex pretreatments such as segmentation and edge detection. And it can improve the inpainting quality of texture and structure information in the video. Experimental results show-that the inpainting quality of the proposed algorithm is superior to that of the existing video inpainting algorithms.关键词
视频修复/Surfacelet变换/稀疏重构Key words
video inpainting/ Surfacelet transform/ sparse reconstruction分类
信息技术与安全科学引用本文复制引用
江山,尹忠科,陈帆..基于Surfacelet稀疏重构的视频修复[J].数据采集与处理,2012,27(4):444-449,6.基金项目
中央高校基本科研业务专项基金(SWJTU09CX039,SWJTU10CX09)资助项目. （SWJTU09CX039,SWJTU10CX09）
