Criminisi algorithm based on marginal structure for image inpainting

LI Zun; WU Jin; LIU Jin

doi:10.3788/YJYXS20142905.0756

您当前的位置：

首页 >

文章列表页 >

Criminisi algorithm based on marginal structure for image inpainting

Table of contents | 更新时间：2020-08-12

- Criminisi algorithm based on marginal structure for image inpainting
- Chinese Journal of Liquid Crystals and Displays Vol. 29, Issue 5, Pages: 756-760(2014)
- 作者机构：
  
  武汉科技大学信息科学与工程学院,湖北武汉,430081
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20142905.0756
  CLC： TP391.41
- Received：17 January 2014，
  
  Revised：25 February 2014，
  
  Published：05 October 2014
- 稿件说明：
移动端阅览
李尊, 吴谨, 刘劲. 基于边缘结构的Criminisi图像修复[J]. 液晶与显示, 2014,29(5): 756-760

LI Zun, WU Jin, LIU Jin. Criminisi algorithm based on marginal structure for image inpainting[J]. , 2014,29(5): 756-760
李尊, 吴谨, 刘劲. 基于边缘结构的Criminisi图像修复[J]. 液晶与显示, 2014,29(5): 756-760 DOI： 10.3788/YJYXS20142905.0756.

LI Zun, WU Jin, LIU Jin. Criminisi algorithm based on marginal structure for image inpainting[J]. , 2014,29(5): 756-760 DOI： 10.3788/YJYXS20142905.0756.

摘要

为了提高图像边缘结构信息的修复效果，本文优化的Criminisi算法优先权，侧重于提高数据项的鲁棒性，并在全局搜索寻找最佳匹配模块进行修复。且在修复结束后，对修复区域进行FDIM算法的无缝拼接处理，使图像的整体和谐统一。实验证明，该修复方法能够很好地处理边缘结构细节信息，并降低了错误匹配，满足人的视觉需求，具有相对较高的实用价值。

Abstract

In order to improve the inpainting effect of marginal structure

the priority of optimized Criminisi algorithm focuses on improving the robustness of a data item in this paper

and then the optimized Criminisi algorithm searches for the best matching module in global image. After these

this paper uses FDIM which is a kind of seamless splicing algorithms in repair region

which makes a harmony of the whole image. Lots of experiments prove that this method can deal with the details of marginal structure effectively and reduce the inaccurate matching as well as meets the demand of human visual

so this method has relatively high practical value.

关键词

Keywords

references

Bertalmio M, Sapiro G, Caselles V,et al.Image inpainting[C].Proceedings of International Conference on Conputer Graphics and Interactive Techniques,USA:John Seely Brown,2000:417-424.[2] 沈峘, 李舜酩, 毛建国,等. 数字图像复原技术综述[J]. 中国图象图形学报, 2009, 14(9):1764-1775. Shen H, Li S M, Mao J G,et al.Digital image restoration techniques a review[J].Journal of Image and Graphics,2009,14(9):1764-1775.(in Chinese)[3] Ballester C, Bertalmio M, Caselles V,et al.Filling-in by joint interpolation of vector field and gray levels[J].IEEE Trans. Image Process,2001,10(8): 1200-1211.[4] Chan T, Shen F. Mathematical models for local non-texture inpaintings[J].SIAM Journal on Applied Mathema-tics,2002, 62(3):1019-1043.[5] Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar based inpainting[J].IEEE Trans. Image Process,2004, 13(9):1200-1212.[6] 赵伦. 一种基于样本纹理的图像修复算法研究[J]. 电脑知识与技术, 2013, 9(19):4509-4528. Zhao L.An image restoration algorithm based on the sample texture[J].Computer Knowledge And Technology,2013,9(19):4509-4528. (in Chinese)[7] 常晨, 尹立新, 方宝龙. 一种改进的Criminisi图像修复算法[J]. 计算机应用与软件, 2012,29(9):238-267. Chang C, Yin L X, Fang B L. An improved criminisi algorithm for image inpainting[J].Computer Applications and Software,2012,29(9):238-267. (in Chinese)[8] 张斐. 大区域图像修复算法研究[D]. 南京:南京邮电大学,2013. Zhang F. Research on large area image inpainting[D].Nanjing: Nanjing University of Posts and Telecommunications,2013. (in Chinese)[9] 刘洋,王昊京,田小建,等. 采用区域分割的变尺寸样本块高效图像修复[J]. 光学精密工程, 2010,18(12):2657-2664. Liu Y, Wang H J, Tian X J,et al.Efficient image inpainting based on region segmentation and varying exemplar[J].Optics and Precision Engineering, 2010,18(12):2657-2664. (in Chinese)[10] 邵明省,杜广朝. 基于量子克隆多宇宙算法的图像融合研究[J]. 液晶与显示, 2012,27(6);837-841. Shao M S,Du G C. Image fusion processing based on multi-universe quantum cloning algorithm[J].Chinese Journal of Liquid Crystals and Diaplays,2012,27(6);837-841. (in Chinese)[11] 张焕龙. 图像无缝拼接技术的研究[D]. 开封:河南大学, 2007. Zhang H L.Research on seamless image mosaic technology[D].Kaifeng:Henan University,2007. (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Second-order image restoration based on gated convolution and attention transfer

Virtual viewpoint image generation method based on deep convolutional neural network in autostereoscopic display

Fast Criminisi image inpainting based on firefly algorithm

Related Author

PENG Yan-fei

GU Li-rui

WANG Gang

Ao-wei FU

Min ZHAO

Ling LUO

Yan XING

Huan DENG

Related Institution

School of Electronic and Information Engineering， Liaoning Technical University

Bohai Shipbuilding Vocational College

School of Electronics and Information Engineering, Sichuan University

School of Instrumentation and Optoelectronic Engineering, Beihang University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰