自相似性匹配的纹理合成

计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 215-219.

自相似性匹配的纹理合成

朱瑞超,钱文华,普园媛,徐丹

云南大学计算机科学与工程系昆明650504

出版日期:2018-06-20 发布日期:2018-08-03
作者简介:朱瑞超(1996-),男,CCF学生会员,主要研究方向为图像处理、非真实感绘制等;钱文华(1980-),男,博士,副教授,CCF会员,主要研究方向为图像处理、非真实感绘制等;普园媛(1972-),女,博士,教授,CCF会员,主要研究方向为非真实感绘制、图像情感分析等;徐丹(1968-),女,博士,教授,博士生导师,CCF会员,主要研究方向为模式识别、虚拟现实等。
基金资助:
国家自然科学基金(61662087,61462093,61163019),云南省应用基础研究计划(2014FA021,2014FB113),云南省教育厅重点项目(2015Z012)资助

Texture Synthesis Based on Self-similarity Matching

ZHU Rui-chao,QIAN Wen-hua,PU Yuan-yuan, XU Dan

School of Information Science and Engineering,Yunnan University,Kunming 650504,China

Online:2018-06-20 Published:2018-08-03

摘要/Abstract

摘要： 基于Image Quilting算法,基于块匹配的误差提出了一种基于自相似匹配的改进方法,其有效提高了缝合速度及合成质量,对不同纹理样本都能取得较好的合成效果。该算法首先根据样本图像大小动态确定匹配块的大小;之后通过自相似匹配的原理设置了缝合块的边界匹配误差,保留了缝合块的边界信息;在缝合过程中使用贪心算法选取相似性最高的块作为下一个待缝合的块,通过局部最优合成效果合成最终纹理图像。实验结果表明,改进后的算法减少了合成时间,消除了匹配块之间的不连续性,提高了合成质量。

关键词: Image Quilting算法, 贪心算法, 纹理合成, 自相似匹配

Abstract: Image Quilting algorithm is a classical algorithm of texture synthesis based on the sample,but the speed and suture effect still need to be improved.Based on the error of block matching,an improved method based on self-similar matching was proposed.The improved algorithm can effectively improve the stitching speed,enlarge the range of application and synthesis quality.The algorithm first determines the matching block size according to the sample size by dynamic pattern.Then on the principle of self-similar matching,it sets block boundary matching error and retains the suture block boundary information.In the process of stitching,the greedy algorithm is used to select the block with the highest degree of coincidence as the next block to be stitched.The experimental results show that the improved algorithm improves the time efficiency of the synthesis,enhances the stitching effect between the blocks,and improves the final synthesis effect.

Key words: Greedy algorithm, Image Quilting algorithm, Self-similarity matching, Texture synthesis

中图分类号:

TP391

朱瑞超,钱文华,普园媛,徐丹. 自相似性匹配的纹理合成[J]. 计算机科学, 2018, 45(6A): 215-219. https://doi.org/

ZHU Rui-chao,QIAN Wen-hua,PU Yuan-yuan, XU Dan. Texture Synthesis Based on Self-similarity Matching[J]. Computer Science, 2018, 45(6A): 215-219. https://doi.org/

参考文献

[1]杜常青,钱文华.二维纹理合成算法优化研究[J].计算机科学,2013,40(4):314-316.
[2]EFROS A A,FREEMAN W T.Image Quilting for Texture Synthesis and Transfer[C]∥Proceedings of the 28th Annual Conference on Computer Graphic Sand Interactive Techniques.2001:341-346.
[3]KWATRA V,SCHODL A,ESSA I.Graph-cut Textures:Image and Video Synthesis Using Graph Cuts[J].Proceedings of the ACM Transactions on Graphics,2003,22(3):277-286.
[4]COHENMF,SHADEJ,HILLERS,et al.Wang tiles for image and texture generation[J].ACM Transactions on Graphics,2003,22(3):287-294.
[5]孙劲光,刘双九.块尺寸自适应的Tile纹理合成算法[J].计算机工程与应用,2016,52(11):164-168.
[6]孟春芝,何凯,张伟伟.自适应选取样本块大小的纹理合成方法[J].计算机工程与应用,2012,48(17):170-173.
[7]聂俊岚,王艳芬.块纹理合成中纹理块尺寸自适应算法[J].计算机辅助设计与图形学学报,2008,20(10):1353-1357.
[8]岳晓菊,康宝生,闫丽君.利用相关性原理纹理合成的改进算法[J].计算机工程与应用,2011,47(10):190-192.
[9]潘璐璐,延伟东,郑红婵.基于多尺度局部自相似性和邻域嵌入的超分辨率算法研究[J].西北工业大学学报,2015(6):1014-1019.
[10]胡修兵.异源图像匹配自相似性测度的快速算法[J].科技创新与应用,2017(6):102.
[11]穆晓敏,杨倩,王植存.图像的自相似性研究[J].郑州大学学报(理学版),2005,37(2):67-69.
[12]林定,陈崇成,唐丽玉,等.基于Image Quilting算法的纹理合成[J].系统仿真学报,2008(S1):381-384.
[13]丛波.基于MATLAB的数字图像处理技术及应用[J].中国科技信息,2011(5):85-86.

相关文章 15

[1]	张翀宇, 陈彦明, 李炜. 边缘计算中面向数据流的实时任务调度算法 Task Offloading Online Algorithm for Data Stream Edge Computing 计算机科学, 2022, 49(7): 263-270. https://doi.org/10.11896/jsjkx.210300195
[2]	刘漳辉, 郑鸿强, 张建山, 陈哲毅. 多无人机使能移动边缘计算系统中的计算卸载与部署优化 Computation Offloading and Deployment Optimization in Multi-UAV-Enabled Mobile Edge Computing Systems 计算机科学, 2022, 49(6A): 619-627. https://doi.org/10.11896/jsjkx.210600165
[3]	靳利贞, 李庆忠. 基于接缝一致性准则的结构纹理图像快速合成算法 Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion 计算机科学, 2022, 49(6): 262-268. https://doi.org/10.11896/jsjkx.210400039
[4]	张新明, 李双倩, 刘艳, 毛文涛, 刘尚旺, 刘国奇. 信息共享模型和组外贪心策略的郊狼优化算法 Coyote Optimization Algorithm Based on Information Sharing and Static Greed Selection 计算机科学, 2020, 47(5): 217-224. https://doi.org/10.11896/jsjkx.190400039
[5]	胡俊钦, 张佳俊, 黄引豪, 陈星, 林兵. 边缘环境下DNN应用的计算迁移调度技术 Computation Offloading Scheduling Technology for DNN Applications in Edge Environment 计算机科学, 2020, 47(10): 247-255. https://doi.org/10.11896/jsjkx.190900106
[6]	李卓, 徐哲, 陈昕, 李淑琴. 面向移动群智感知的位置相关在线多任务分配算法 Location-related Online Multi-task Assignment Algorithm for Mobile Crowd Sensing 计算机科学, 2019, 46(6): 102-106. https://doi.org/10.11896/j.issn.1002-137X.2019.06.014
[7]	郭小英, 李亮, 耿海军. 合成纹理图像的视觉相似性眼动分析 Eye-movement Analysis of Visual Similarity Perception on Synthesized Texture Images 计算机科学, 2018, 45(8): 223-228. https://doi.org/10.11896/j.issn.1002-137X.2018.08.040
[8]	陈晋音,胡可科,李玉玮. 基于MB-RRT^的无人机多点航迹规划算法研究 Research on UAV Multi-point Navigation Algorithm Based on MB-RRT^ 计算机科学, 2018, 45(6A): 85-90.
[9]	胡庆成, 张勇, 邢春晓. 基于有重叠社区划分的社会网络影响最大化方法研究 K-clique Heuristic Algorithm for Influence Maximization in Social Network 计算机科学, 2018, 45(6): 32-35. https://doi.org/10.11896/j.issn.1002-137X.2018.06.005
[10]	孙焘,朱晓明. 基于格代数的最长公共子序列近似求解 Computing Longest Common Subsequences Approximately Based on Lattice 计算机科学, 2017, 44(2): 270-274. https://doi.org/10.11896/j.issn.1002-137X.2017.02.045
[11]	蔡国永,裴广战. 基于LT⁺模型的社交网络影响力最大化研究 Influence Maximization Based on LT⁺ Model in Social Networks 计算机科学, 2016, 43(9): 99-102. https://doi.org/10.11896/j.issn.1002-137X.2016.09.018
[12]	汤颖,林琦峰,肖廷哲,范菁. 基于GPU加速的保结构纹理合成 GPU-based Texture Synthesis with Preserved Structures 计算机科学, 2016, 43(4): 299-302. https://doi.org/10.11896/j.issn.1002-137X.2016.04.061
[13]	孙劲光,刘双九. 基于人工蜂群的D-Tile纹理合成算法 D-Tile for Texture Synthesis Based on Artificial Bee Colony 计算机科学, 2015, 42(2): 287-291. https://doi.org/10.11896/j.issn.1002-137X.2015.02.061
[14]	汤颖,肖廷哲,范菁. 基于GPU加速的快速图像相似区域查找 GPU-based Fast Search of Similar Patches in Images 计算机科学, 2014, 41(2): 290-296.
[15]	王俊,余伟,胡亚慧,李石君. 基于3-layer中心度的社交网络影响力最大化算法 Heuristic Algorithm Based on 3-layer Centrality for Influence Maximization in Social Networks 计算机科学, 2014, 41(1): 59-63.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed