Fast image completion algorithm based on random correspondence

doi:10.11772/j.issn.1001-9081.2014.06.1719

Journal of Computer Applications ›› 2014, Vol. 34 ›› Issue (6): 1719-1723.DOI: 10.11772/j.issn.1001-9081.2014.06.1719

Previous Articles Next Articles

Fast image completion algorithm based on random correspondence

XIAO Mang¹,LI Guangyao¹,TAN Yunlan¹,²,GENG Ruijin¹,LV Yangjian¹,XIE Li¹,PENG Lei¹

1. College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China;
2. School of Electronics and Information Engineering, Jinggangshan University, Ji'an Jiangxi 343009, China

Received:2013-12-10 Revised:2014-01-30 Online:2014-07-02 Published:2014-06-01
Contact: XIAO Mang

基于随机映射的快速图像修复算法

肖莽¹,李光耀¹,谭云兰¹,²,耿瑞全¹,吕扬建¹,谢力¹,彭磊¹

1. 同济大学电子与信息工程学院,上海 201804
2. 井冈山大学电子与信息工程学院,江西吉安 343009

通讯作者: 肖莽
作者简介:肖莽(1982-),男,江西吉安人,博士研究生,主要研究方向:数字图像处理,机器学习;李光耀(1965-),男,安徽安庆人,教授,博士,主要研究方向:图形图像学、虚拟现实;谭云兰(1972-),女,江西吉安人,副教授,博士研究生,主要研究方向:数字图像处理;耿瑞全(1990-),男,安徽安庆人,硕士研究生,主要研究方向:数字图像处理;吕扬建(1990-),男,浙江温州人,硕士研究生,主要研究方向:数字图像处理;谢力(1989-),男,浙江台州人,硕士研究生,主要研究方向:数字图像处理;彭磊(1977-),男,山东泰安人,博士研究生,主要研究方向:数字图像处理。
基金资助:
国家自然科学基金资助项目

Abstract

Abstract:

The traditional patch-based image completion algorithms circularly search the most similar patches in the whole image, and are easily affected by confidence factor in the process of structure propagation. As a result, these algorithms have poor efficiency and need a lot of time for the big computation. To overcome these shortages, a fast image completion algorithm based on randomized correspondence was proposed. It adopted a randomized correspondence algorithm to search the sample regions, which have similar structure and texture with the target region, so as to reduce the search space. Meanwhile, the method of computing filling priorities based on confidence factor and edge information was optimized to enhance the correctness of structure propagation. In addition, the method of calculating the most similar patches was improved. The experimental results show that, compared with the traditional algorithms, the proposed approach can obtain 5-10 times speed-up in repair rate, and performs better in image completion.

摘要：

传统基于样本块的图像修复方法是在图像全局区域内循环搜索最优相似块,且结构传播过程易受置信因子影响,使得算法运算量大、时间长、效率低。针对以上问题,提出基于随机映射的修复算法。该算法采用随机映射的方法搜索与待修复区域在结构和纹理相似的样本区域,去除冗余的样本搜索空间;其次优化了基于置信因子和边缘信息的优先级计算方法,改进了最优相似块的计算方法,增强了图像结构传播的正确性。实验结果表明,该方法的修复速度比传统方法提高了5~10倍,且增强了图像修复效果。

CLC Number:

TP391.41

XIAO Mang LI Guangyao TAN Yunlan GENG Ruijin LV Yangjian XIE Li PENG Lei. Fast image completion algorithm based on random correspondence[J]. Journal of Computer Applications, 2014, 34(6): 1719-1723.

肖莽李光耀谭云兰耿瑞全吕扬建谢力彭磊. 基于随机映射的快速图像修复算法[J]. 计算机应用, 2014, 34(6): 1719-1723.

References

[1]BERTALMIO M, SAPIRO G, CASELLES V, et al. Image inpainting[C]// Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press, 2000: 417-424.
[2]EFROS A A, LEUNG T K. Texture synthesis by non-parametric sampling[C]// ICCV 1999: Proceedings of the 7th IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 1999, 2: 1033-1038.
[3]CRIMINISI A, PEREZ P, TOYAMA K. Region filling and object removal by exemplar-based image inpainting [J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200-1212.
[4]CHENG W-H, HSIEH C-W, LIN S-K, et al. Robust algorithm for exemplar-based image inpainting[EB/OL].[2012-10-10]. http://cmlab.csie.org/new_cml_website/media/publications/Cheng-2005-RAE.pdf.
[5]LIU J, LU D. Image inpainting via weighted optimization [J]. Journal of Image and Graphics,2011,16(4):528-532. (刘建明,鲁东明.采用加权优化的图像修复[J]. 中国图象图形学报, 2011,16(4):528-532.)
[6]MICHAEL A. Synthesizing natural textures [C]// Proceedings of the 2001 Symposium on Interactive 3D Graphics. New York: ACM Press, 2001: 217-226.
[7]LU P, CHEN M, MA L, et al. Fast structural image completion [J]. Journal of Image and Graphics,2010,15(6):931-935. (路平,陈敏刚,马利庄,等.快速结构化图像修复[J]. 中国图象图形学报, 2010, 15(6):931-935.)
[8]TONG X, ZHANG J, LIU L, et al. Synthesis of bidirectional texture functions on arbitrary surfaces[J]. ACM Transactions on Graphics, 2002, 21(3): 665-672.
[9]BARNES C, SHECHTMAN E, FINKELSTEIN A, et al. PatchMatch: a randomized correspondence algorithm for structural image editing[J]. ACM Transactions on Graphics, 2009, 28(3): Article No. 24.
[10]HE K, SUN J. Computing nearest-neighbor fields via propagation-assisted KD-trees [C]// CVPR 2012: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2012:111-118.
[11]BARNES C, SHECHTMAN E, GOLDMAN D B, et al. The generalized patchmatch correspondence algorithm[C]// Computer Vision — ECCV 2010, LNCS 6313. Berlin: Springer-Verlag, 2010: 29-43.
[12]KOPF J, KIENZLE W, DRUCKER S, et al. Quality prediction for image completion[J]. ACM Transactions on Graphics, 2012, 31(6): Article No. 131.
[13]KOMODAKIS N, TZIRTAS G. Image completion using efficient belief propagation via priority scheduling and dynamic pruning [J]. IEEE Transactions on Image Processing, 2007, 16(11): 2649-2661.

[1]	. Pavement defect detection algorithm with enhanced morphological perception [J]. Journal of Computer Applications, 0, (): 0-0.
[2]	. Data augmentation method for abnormal passenger behavior in elevators based on dynamic graph convolutional network [J]. Journal of Computer Applications, 0, (): 0-0.
[3]	. Text-based person retrieval method based on multi-granularity shared semantic center association [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Image Caption Method Based on Swin-Transformer and Multi-Scale Feature Fusion [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	Keyi FU, Gaocai WANG, Man WU. Few-shot object detection method based on improved region proposal network and feature aggregation [J]. Journal of Computer Applications, 2024, 44(12): 3790-3797.
[6]	Yudong PANG, Zhixing LI, Weijie LIU, Tianhao LI, Ningning WANG. Small target detection model in overlooking scenes on tower cranes based on improved real-time detection Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3922-3929.
[7]	Xin ZHAO, Xinjie LI, Jian XU, Buyun LIU, Xiang BI. Parallel medical image registration model based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2024, 44(12): 3915-3921.
[8]	. 3D object detection algorithm based on multiscale network with axial attention [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Few-shot skin image classification model based on spatial transformation and feature distribution calibration [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	. Multi-target detection algorithm for traffic intersection images based on YOLOv9 [J]. Journal of Computer Applications, 0, (): 0-0.
[11]	. Semi-supervised object detection framework guided by self-paced learning#br# [J]. Journal of Computer Applications, 0, (): 0-0.
[12]	Yaobin ZOU, Bin ZHANG. Automatic thresholding method guided by maximizing four-directional weighted Shannon entropy [J]. Journal of Computer Applications, 2024, 44(11): 3565-3573.
[13]	Tao LIU, Shihong JU, Yimeng GAO. Small object detection algorithm from drone perspective based on improved YOLOv8n [J]. Journal of Computer Applications, 2024, 44(11): 3603-3609.
[14]	Yusheng LIU, Xuezhong XIAO. High-fidelity image editing based on fine-tuning of diffusion model [J]. Journal of Computer Applications, 2024, 44(11): 3574-3580.
[15]	Lihua HU, Xiaoping LI, Jianhua HU, Sulan ZHANG. Multi-view stereo method based on quadtree prior assistance [J]. Journal of Computer Applications, 2024, 44(11): 3556-3564.

Fast image completion algorithm based on random correspondence

基于随机映射的快速图像修复算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics