Image inpainting algorithm based on double cross TV

被引：1

作者：

Zhai, Dong-Hai ^{[1
,2
]}

Duan, Wei-Xia ^{[1
]}

Yu, Jiang ^{[1
]}

机构：

[1] School of Information Science and Technology, Southwest Jiaotong University

[2] Engineering School, Tibet University

来源：

Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | 2014年 / 43卷 / 03期

关键词：

Double cross TV algorithm; Image inpainting; Inpainting accuracy; Neighborhood information;

D O I：

10.3969/j.issn.1001-0548.2014.03.020

中图分类号：

学科分类号：

摘要：

The various total variation (TV) algorithms currently reconstruct the lost or deteriorated parts of images by related information of damaged pixel and its 4 neighborhood pixels. Their inpainting accuracy is low because of finite related information. The double cross TV algorithm proposed in this paper divides 8 neighborhood pixels into 2 groups, and computes the pixel value of damaged pixel by using 4 neighborhood pixels in each group respectively. Therefore, the weighted mean of these two pixel values is the final inpainting pixel value. The Experiments show an improvement in PSNR and less iteration number compared with the original TV.

引用

页码：432 / 436

页数：4

共 13 条

[1]

Chan T., Esedoglu S., Park F., Et al., Recent developments in total variation image restoration, Mathematical Models in Computer Vision: The Handbook, (2004)

[2]

Criminisi A., Toyama K., Object removal by exemplar-based inpainting, IEEE Computer Society Conf on Computer Vision and Pattern Recognition, (2003)

[3]

Tang C.-W., Hu X., Chen L., Et al., Sample-based image completion using structure synthesis, J Vis Commun Image R, 24, pp. 1115-1123, (2013)

[4]

Bertalmio M., Sapiro G., Caselles V., Et al., Image inpainting, Proc of the 27th Ann Conf on Comp Graph and Interactive Tech, pp. 417-427, (2000)

[5]

Niang O., Thioune A., El G., Et al., Partial differential equation-based approach for empirical mode decomposition: Application on Image Analysis, IEEE Trans on Image Processing, 9, 21, pp. 3991-4001, (2012)

[6]

Chan T., Shen J., Mathematical models for local non-texture inpaintings, SIAM Journal on Applied Mathematics, 62, pp. 1019-1043, (2001)

[7]

Chan T., Shen J., Non-texture inpaintings by curvature-driven diffusions(CDD), Visual Comm Image Rep, 12, 4, pp. 436-449, (2001)

[8]

Rudin L.I., Osher S., Fatemi E., Nonlinear total variation based noise removal algorithms, Physical D, 60, pp. 259-268, (1992)

[9]

Li F., Bao Z., Liu R.-H., Et al., Fast image inpainting and colorization by Chambolle's dual method, J Vis Commun Image R, 22, pp. 529-542, (2011)

[10]

Shi Y.-Y., Wang L.-L., Tai X.-C., Geometry of total variation regularized model, Journal of Computational and Applied Mathematics, 8, 236, pp. 2223-2234, (2012)

← 1 2 →