A novel exemplar-based non-local algorithm for image inpainting

被引:0
作者
Yang G. [1 ,2 ]
Yang F. [2 ,3 ]
Zhuang X. [1 ]
机构
[1] School of Electronic and Information Engineering, Qingdao University, Qingdao
[2] School of Technology, Nanjing Audit University, Nanjing
[3] School of Information Engineering, Nanchang Hangkong University, Nanchang
来源
International Journal of Simulation: Systems, Science and Technology | 2016年 / 17卷 / 31期
基金
中国国家自然科学基金;
关键词
Criminisi algorithm; Emeplar-based; Hausdorff distance; Image inpainting; Non-local means;
D O I
10.5013/IJSSST.a.17.4.139
中图分类号
学科分类号
摘要
A novel exemplar-based image inpainting algorithm using the Non-Local Means (NLM) algorithm and Criminisi algorithm is proposed. In order to decrease the error in match rate, the new algorithm adopts the sum of squared differences (SSD) search method for several exemplars to generate a candidate exemplar set. Then it determines the Hausdorff distance as measurement criterion to find a match block by computing the weighted average of the exemplar set so that the image edge structure is preferentially propagated. Experimental results demonstrate that the improved algorithm keeps the image structure better and obtains better visual appearance. © 2016, UK Simulation Society. All rights reserved.
引用
收藏
页码:39.1 / 39.5
相关论文
共 12 条
[1]  
Muddala S.M., Sjostrom M., Olsson R., Virtual view synthesis using layered depth image generation and depth-based inpainting for filling disocclusions and translucent disocclusions, Journal of Visual Communication and Image Representation, 38, pp. 351-366, (2016)
[2]  
Barbu T., Variational image inpainting technique based on nonlinear second-order diffusions, Computers & Electrical Engineering, 23, (2016)
[3]  
Bertalmio M., Sapiro G., Gaselles V., Et al., Image inpainting, Proceedings of the 27Th Annual Conference on Computer Raphics, pp. 417-424, (2000)
[4]  
Chan T.F., Shen J.H., Mathematical models for local nontexture inpainting, SIAM Journal of Applied Mathematics, 62, pp. 1019-1043, (2001)
[5]  
Chan T.F., Shen J.H., Non-texture inpainting by curvaturedriven diffusions, Journal of Visual Communication and Image Representation, 12, pp. 436-449, (2001)
[6]  
Bertalmio M., Vese L., Sapiro G., Et al., “Simultaneous structure and texture image inpainting, IEEE Transactions on Image Processing, 12, pp. 18-20, (2003)
[7]  
Drori I., Cohenor D., Yeshurun H., Fragment-based image completion, ACM Transactions on Graphics, 22, pp. 303-312, (2003)
[8]  
Criminisi A., Perez P., Toyama K., Region filling and object removal by exemplar-based inpainting, IEEE Computer Transactions on Image Processing, 13, pp. 1200-1212, (2004)
[9]  
Wong A., Orchard J., A nonlocal-means approach to exemplarbased inpainting, ICIP, pp. 2600-2603, (2008)
[10]  
Tang F., Ying Y.T., Wang J., Et al., A novel texture synthesis based algorithm for object removal in photographs, Proceedings of 9Th Asian Computing Science Conference, pp. 248-258, (2004)