Exemplar-based Image Inpainting using Structure Tesnor

被引:0
作者
Liu Kui [1 ]
Tan Jieqing [1 ]
Su Benyue
机构
[1] Hefei Univ Technol, Sch Comp & Informat, Hefei 230009, Peoples R China
来源
PROCEEDINGS OF THE 2013 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE AND ELECTRONICS INFORMATION (ICACSEI 2013) | 2013年 / 41卷
关键词
Image inpainting; texture synthesis; exemplar; structure tensor; structural similarity (SSIM); DIFFUSION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Exemplar-based image inpainting techniques face two main problems. One is the decision of filling-in order which has a strong impact on image inpainting effect. Another problem is greedy search process while searching for the best exemplar patch. This paper presents a robust method for exemplar-based image inpainting based on structure tensor. The novel priority function is redefined. Experimentation results show that our image inpainting method improves the quality of image inpainting compared with the conventional exemplar-based image completion algorithms.
引用
收藏
页码:619 / 623
页数:5
相关论文
共 15 条
[1]  
[Anonymous], COMP SUPPL
[2]   Image inpainting [J].
Bertalmio, M ;
Sapiro, G ;
Caselles, V ;
Ballester, C .
SIGGRAPH 2000 CONFERENCE PROCEEDINGS, 2000, :417-424
[3]  
Bornard R., 2002, P ACM INT C MULTIMED, P355
[4]  
Chan T. F., 2001, 0112 CAM UCLA DEP MA
[5]   Nontexture inpainting by curvature-driven diffusions [J].
Chan, TF .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2001, 12 (04) :436-449
[6]   Mathematical models for local nontexture inpaintings [J].
Chan, TF ;
Shen, JH .
SIAM JOURNAL ON APPLIED MATHEMATICS, 2002, 62 (03) :1019-1043
[7]  
Chang IC, 2013, MULTIMEDIA SECURITY: WATERMARKING, STEGANOGRAPHY, AND FORENSICS, P275
[8]  
CHENG WH, 2005, P INT C COMP GRAPH I
[9]   Region filling and object removal by exemplar-based image inpainting [J].
Criminisi, A ;
Pérez, P ;
Toyama, K .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (09) :1200-1212
[10]  
Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383