首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51005--1)

基于匹配误差改进和迭代传输的纹理传输算法

Texture Transfer Algorithm Based on Matching Error Improvement and Iterative Transfer

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

基于样本块的纹理传输原理,研究了纹理图像的边缘梯度信息、最小误差路径以及非线性亮度/色度型(YUV)颜色空间的亮度信息对纹理传输结果的影响。在误差度量时,将纹理图像本身的边缘梯度信息和重叠区域的最小误差路径同时作为纹理合成时的度量,并引入源纹理图像和目标图像在YUV颜色空间的亮度信息作为纹理传输的约束度量,能使找到的匹配块更适合纹理传输。同时,在纹理传输过程中采用迭代的方法,解决了大部分纹理通过一次传输后的传输效果不佳的问题。实验结果表明,改进后的纹理传输算法能取得较传统纹理传输算法更好的传输效果。

Abstract

Based on texture transfer principle of sample blocks, the influences of edge gradient information of texture image, the minimum error path and luminance information in the nonlinearity luma/chroma (YUV) color space on texture transfer results are studied. We take edge gradient information of texture image and the minimum error path of overlapping region as the measure of the texture synthesis at the same time, and introduce luminance information of the source texture image and the target image in YUV color space as constraint measure of the texture transmission. The found matching block is more suitable for texture transfer. At the same time, we use iterative method in the process of texture transmission to solve the problem that the transmission effect is not good after the texture transmission for one time. Experimental results show that, compared with the traditional texture transfer algorithm, the improved texture transfer algorithm can achieve better transmission effect.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/lop55.051005

所属栏目:图像处理

基金项目:贵州省教育厅青年科技人才成长项目[黔教合KY字(2017)335]、贵州省科技合作计划[黔科合LH字(2017)7161号,黔科合LH字(2016)7318号,黔科合LH字(2015)7744号]、国家自然科学基金(11464023)

收稿日期:2017-10-25

修改稿日期:2017-11-13

网络出版日期:--

作者单位    点击查看

谭永前:凯里学院大数据工程学院, 贵州 凯里 556001
曾凡菊:凯里学院大数据工程学院, 贵州 凯里 556001重庆大学光电工程学院, 重庆 400044

联系人作者:谭永前(tanyongqian1@163.com)

备注:谭永前(1984—),男,硕士,讲师,主要从事图形图像处理和光电材料方面的研究。E-mail: tanyongqian1@163.com

【1】Efros A A, Freeman W T. Image quilting for texture synthesis and transfer[C]. Proceeding of the 28th Annual Conference on Computer Graphics and Interactive Techniques, 2001: 341-346.

【2】Kwatra V, Schoedl A, Essa I, et al. Graphcut textures: image and video synthesis using graph cuts[C]. Proceedings of ACM Transactions on Graphics, 2003: 277-286.

【3】Busto P P, Eisenacher C, Lefebvre S, et al. Instant texture synthesis by numbers[C]. Proceedings of the Vision, Modeling and Visualization Workshop, 2010: 81-85.

【4】Cohen M F, Shade J, Hiller S, et al. Wang Tiles for image and texture generation[C]. Annual Symposium of the ACM SIGGRAPH, 2003: 287-294.

【5】Tan Y Q, Zeng F J, Yue L, et al. An improved texture image synthesis algorithm[J]. Laser & Optoelectronics Progress, 2016, 53(12): 121001.
谭永前, 曾凡菊, 岳莉, 等. 一种改进的纹理图像合成算法[J]. 激光与光电子学进展, 2016, 53(12): 121001.

【6】Wang D H, Dong L, Du H M.A study on the algorithms for 2D texture mapping and its employment in hardware design[C]. Proceedings of the 2012 International Conference on Computer Application and System Modeling, 2012: 1271-1274.

【7】Lukac M, Fiser J, Bazin J C, et al. Painting by feature: texture boundaries for example-based image creation[C]. Proceedings of ACM Transactions on Graphics, 2013, 32(4): 116.

【8】Lee H S.A new image super resolution by texture transfer[C]. IEEE International Conference on Image Processing, 2014: 3915-3918.

【9】Zhou R H. Texture synthesis algorithm and its application in the texture transmission[D]. Jinan: Shandong Normal University, 2015.
周瑞华. 纹理合成算法及其在纹理传输中的应用研究[D]. 济南: 山东师范大学, 2015.

【10】Gatys L A, Ecker A S, Bethge M. Texture synthesis using convolutional neural networks[J]. Febs Letters, 2015, 70(1): 51-55.

【11】Tan Y Q, Zeng F J. Texture transfer technique based on brightness remapping and gradient structure information[J]. Laser & Optoelectronics Progress, 2018, 55(3): 031001.
谭永前, 曾凡菊. 基于亮度重映射和梯度结构信息的纹理传输算法[J]. 激光与光电子学进展, 2018, 55(3): 031001.

【12】Wang Y, Liu H Z, Wu Z H. Edge-preserving smoothing for image decomposition via a hybrid approach[C]. SPIE, 2013, 9069: 90691N.

【13】Du L L, Duan H C. An improvement to the Image quilting texture transfer algorithm[J].Journal of Chinese Computer Systems, 2015, 36(11): 2563-2567.
杜黎黎, 段会川. Image quilting纹理传输算法的改进研究[J].小型微型计算机系统, 2015, 36(11): 2563-2567.

【14】Wen H, Chen Z J. Improved algorithm for texture transfer by introducing edge information[J]. Computer Systems and Applications, 2013, 22(11): 143-147.
文慧, 陈昭炯. 引入边缘信息的纹理传输改进算法[J]. 计算机系统应用, 2013, 22(11): 143-147.

【15】Tan Y Q, Zeng F J. Gradient-based Wang Tiles texture synthesis algorithm with adaptive block size[J]. Laser & Optoelectronics Progress, 2017, 54(5): 051001.
谭永前, 曾凡菊. 基于梯度的块尺寸自适应Wang Tiles纹理合成算法[J]. 激光与光电子学进展, 2017, 54(5): 051001.

引用该论文

Tan Yongqian,Zeng Fanju. Texture Transfer Algorithm Based on Matching Error Improvement and Iterative Transfer[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051005

谭永前,曾凡菊. 基于匹配误差改进和迭代传输的纹理传输算法[J]. 激光与光电子学进展, 2018, 55(5): 051005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF