|本期目录/Table of Contents|

[1]何凯,高俊俏,卢雯霞.基于改进置信度函数及匹配准则的图像修复算法[J].天津大学学报(自然科学版),2017,(04):399-404.[doi:10.11784/tdxbz201603091]
 He Kai,Gao Junqiao,Lu Wenxia.Image Inpainting Algorithm Based on Improved Confidence Function and Matching Criterion[J].Journal of Tianjin University,2017,(04):399-404.[doi:10.11784/tdxbz201603091]
点击复制

基于改进置信度函数及匹配准则的图像修复算法()
分享到:

《天津大学学报(自然科学版)》[ISSN:0493-2137/CN:12-1127/N]

卷:
期数:
2017年04
页码:
399-404
栏目:
电气自动化与信息工程
出版日期:
2017-04-30

文章信息/Info

Title:
Image Inpainting Algorithm Based on Improved Confidence Function and Matching Criterion
作者:
何凯 高俊俏 卢雯霞
天津大学电气自动化与信息工程学院,天津 300072
Author(s):
He Kai Gao Junqiao Lu Wenxia
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
关键词:
图像修复 纹理合成 置信度更新 SSD匹配准则
Keywords:
image inpainting texture synthesis confidence update SSD matching criterion
分类号:
TP391
DOI:
10.11784/tdxbz201603091
文献标志码:
A
摘要:
传统基于纹理合成的图像修复算法, 其置信度值会随着修复过程的进行迅速衰减并趋近于0, 这会导致优先权计算结果不可靠, 产生错误的引导修复方向.除此之外, 传统方法通常采用最小绝对差平方和(SSD)准则来寻找最优匹配块, 匹配准则单一, 精度有限, 容易产生误匹配.为解决上述问题, 提出一种新的置信度更新函数, 以抑制置信度衰减过快的现象, 提高引导修复方向的准确性; 同时引入Census变换匹配准则, 将其与传统SSD匹配准则相结合, 以提高匹配精度.实验仿真结果表明, 本文算法鲁棒性较高且引导方向准确, 对于复杂的结构图像仍然能够获得理想的修复效果.
Abstract:
In the traditional texture synthesis algorithms,the highest confidence value tends to reach zero rapidly with the process of inpainting,which will lead to an unreliable priority result as well as a misguided inpainting direction. In addition,the traditional methods usually search for optimal matching block using the sum of squared differences(SSD)criterion. In this way,the mismatches are inevitable because of the single matching criterion and the limited degree of precision. Therefore,a new confidence update function is proposed to avoid the rapid decay of confidence,which is helpful for improving the accuracy of guided inpainting direction. At the same time,matching accuracy is improved by combining Census transformation matching criterion with the traditional SSD. Experimental results show that the proposed algorithm is more robust,has higher accuracy in guiding direction and achieves a better effect even for the images with complex structure.

参考文献/References:

[1] Chan T F, Shen J. Non-texture inpainting by curvature-driven diffusions(CCD)[J]. Journal of Visual Communication and Image Representation, 2001, 12(4):436-449.
[2] Esedoglu S, Shen J. Digital inpainting based on the Mumford-Shah-Euler image model [J]. European Journal on Applied Mathematics, 2002, 13(4):353-370.
[3] Chan T F, Shen J. Mathematical models for local non-texture inpainting [J]. SIAM Journal of Applied Mathematics, 2001, 62(3):1019-1043.
[4] 张红英, 彭启琮. 数字图像修复技术综述[J]. 中国图象图形学报, 2007, 12(1):1-10.
Zhang Hongying, Peng Qicong. A survey on digital image inpainting [J]. Journal of Image and Graphics, 2007, 12(1):1-10(in Chinese).
[5] Criminisi A, Perez P, Toyama K. Object removal by exemplar-based inpainting [C]// Proceedings of 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Wisconsin, USA, 2003:721-728.
[6] Xue Y, Zhang H, Wang F, et al. Exemplar-based image completion using color ratio gradient [C]//Image and Signal Processing. Sanya, China, 2008:569-572.
[7] Bugeau A, Bertalmío M, Caselles V, et al. A comprehensive framework for image inpainting[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2010, 19(10):2634-2645.
[8] 何凯, 焦青兰, 孟春芝, 等. 非均匀纹理图像大区域修复算法[J]. 天津大学学报, 2012, 45(4):314-318.
He Kai, Jiao Qinglan, Meng Chunzhi, et al. Nonregular texture image completion algorithm in large region [J]. Journal of Tianjin University, 2012, 45(4):314-318(in Chinese).
[9] Tang C, Hu X, Chen L, et al. Sample-based image completion using structure synthesis [J]. Journal of Visual Communication & Image Representation, 2013, 24(7):1115-1123.
[10] Zhang X, Liu B. Image completion with patch sparsity-based global optimization [C]// IEEE 2011 3rd Interna-
tional Conference on Computer Research and Development. Shanghai, China, 2011:62-66.
[11] Martinez-Noriega R, Roumy A, Blanchard G. Exemplar-based image inpainting:Fast priority and coherent nearest neighbor search [C]// IEEE International Workshop on Machine Learning for Signal Processing. Stantander, Spain, 2012:1-6.
[12] 郭勇, 王梅. 基于改进样本块的数字图像修复算法研究[J]. 软件导刊, 2013, 12(10):156-158.
Guo Yong, Wang Mei. Research on exemplar based digital improving image inpainting algorithms[J]. Software Guide, 2013, 12(10):156-158(in Chinese).
[13] Xi X Y, Wang F L, Liu Y F. Improved Criminisi algorithm based on a new priority function with the gray entropy [C]// Proceedings of the 2013 9th International Conference on Computational Intelligence and Security. Leshan, China, 2013:214-218.
[14] Nan A, Xi X. An improved Criminisi algorithm based on a new priority function and updating confidence [C]// IEEE 2014 7th International Conference on Biomedical Engineering and Informatics. Dalian, China, 2015:885-889.
[15] 王军政, 朱华健, 李静. 一种基于Census变换的可变权值立体匹配算法[J]. 北京理工大学学报, 2013, 33(7):704-710.
Wang Junzheng, Zhu Huajian, Li Jing, et al. A census transform based stereo matching algorithm using variable support-weight [J]. Transactions of Beijing Institute of Technology, 2013, 33(7):704-710(in Chinese).

相似文献/References:

[1]何 凯,梁 然,张 涛. 基于小波系数相关性的纹理图像快速修复算法[J].天津大学学报(自然科学版),2010,(12):1093.
 HE Kai,LIANG Ran,ZHANG Tao. Fast Texture Image Completion Algorithm Based on Dependencies Between Wavelet Coefficients[J].Journal of Tianjin University,2010,(04):1093.
[2]何 凯,焦青兰,孟春芝,等.非均匀纹理图像大区域修复算法[J].天津大学学报(自然科学版),2012,(04):314.
 HE Kai,JIAO Qing-lan,MENG Chun-zhi,et al.Non-Regular Texture Image Completion Algorithm in Large Region[J].Journal of Tianjin University,2012,(04):314.
[3]何 凯,郑 欢,张丽莹. 基于旋转及尺度空间拓展的图像修复算法[J].天津大学学报(自然科学版),2015,(07):652.[doi:10.11784/tdxbz201312029]
 He Kai,Zheng Huan,Zhang Liying. Image Completion Algorithm Based on Rotation andScale Space Expansion[J].Journal of Tianjin University,2015,(04):652.[doi:10.11784/tdxbz201312029]

备注/Memo

备注/Memo:
收稿日期: 2016-03-31; 修回日期: 2016-06-02.
作者简介: 何凯(1972—), 男, 博士, 副教授.
通讯作者: 何凯, hekai626@163.com.
基金项目: 国家自然科学基金资助项目(61271326).
Supported by the National Natural Science Foundation of China(No. 61271326).
更新日期/Last Update: 2017-04-10