首页 > 论文 > 激光与光电子学进展 > 55卷 > 6期(pp:61012--1)

基于非线性滤波和边缘检测的纹理传输图像风格化处理

Texture Transmission Image Stylized Processing Based on Non-Linear Filtering and Edge Detection

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

摘要

基于样本块纹理传输的原理, 研究了源纹理图像的纹理信息、结构信息以及目标图像的结构信息对纹理传输风格化效果的影响。采用非线性滤波的相对总变差模型对源纹理图像和目标图像进行分解, 消除源纹理图像的结构信息和目标图像的纹理信息;使用纹理传输算法对上述保留信息进行纹理传输;改进的算法避免了传统算法在传输源纹理图像的结构信息时对目标图像结构的覆盖。这样, 目标图像的边缘结构信息与传输结果图进行叠加, 增强了传输结果图的边缘信息, 改善了风格化的效果。实验证明, 改进后的算法比传统算法取得更好的传输风格化效果。

Abstract

Based on the principle of sample block texture transmission, the influences of the source texture image’s texture information and structural information, and the structural information of the target image on the stylistic effect of the texture transfer are studied. The source texture image and target image are decomposed with the relative total variation model of non-filtering for eliminating the structure information of the source texture image and the texture information of the target image. Texture transmission algorithm is used for the texture transmission of the above reserved information image. The improved algorithm avoids covering the target image structure when the structural information of the source texture image transmits in the traditional algorithm. In this way, the edge structure information of the target image and the transmission result image are superimposed, which enhances the edge information of the transmission result graph, and improves the stylized effect. Experimental results show that the improved algorithm can achieve better transmission stylized effect than that of the traditional algorithm.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/lop55.061012

所属栏目:图像处理

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

收稿日期:2017-12-08

修改稿日期:2018-01-03

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
吴位巍:凯里学院大数据工程学院, 贵州 凯里 556001
张鸿筠:凯里学院大数据工程学院, 贵州 凯里 556001

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方面的研究。E-mail: tanyongqian1@163.com

【1】Wang D, Zhou S H, Sang X S. Simulation for pyrography style painting based on texture transfer[J]. Journal of System Simulation, 2010, 22(12): 2929-2933.
王东, 周世生, 桑贤生. 基于纹理传输的烙画风格图像仿真[J]. 系统仿真学报, 2010, 22(12): 2929-2933.

【2】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.

【3】Farbman Z, Fattal R, Lischinski D, et al. Edge-preserving decompositions for multi-scale tone and detail manipulation[J]. ACM Transactions on Graphics, 2008, 27(3): 67.

【4】Subr K, Soler C, Durand F. Edge-preserving multiscale image decomposition based on local extrema[J]. ACM Transactions on Graphics, 2009, 28(5): 147.

【5】Hertzmann A, Jacobs C E, Oliver N, et al. Image analogies[C]∥Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, 2001: 327-340.

【6】Ashikhmin M. Synthesizing natural textures[C]∥Proceedings of the 2001 Symposium on Interactive 3D Graphics, 2001: 217-226.

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

【8】Tan Y Q, Zeng F J. Texture transfer algorithm 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.

【9】Kwatra V, Schdl A, Essa I, et al.Graphcut textures: image and video synthesis using graph cuts[J]. ACM Transactions on Graphics, 2003, 22(3): 277-286.

【10】Xue F, Cheng C, Jiang J L. Wang tile-based improved texture synthesis[J]. Journal of Computer Applications, 2010, 30(8): 2098-2110.
薛峰, 成诚, 江巨浪. 基于Wang Tile的改进纹理合成算法[J]. 计算机应用, 2010, 30(8): 2098-2110.

【11】Wang J D, Pang M Y, Zhao R B. Texture synthesis using rotational Wang Tiles[J]. Journal of Image and Graphics, 2013, 18(1): 49-54.
王继东, 庞明勇, 赵瑞斌. 旋转的Wang Tiles纹理合成算法[J]. 中国图象图形学报, 2013, 18(1): 49-54.

【12】Xu L, Yan Q, Xia Y, et al. Structure extraction from texture via relative total variation[J]. ACM Transactions on Graphics, 2012, 31(6): 139.

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

【14】Risser E, Han C, Dahyot R, et al. Synthesizing structured image hybrids[J]. ACM Transactions on Graphics, 2010, 29(4): 85.

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

【16】Li W Y, Cheng L D. New progress of fabric defect detection based on computer vision and image processing[J]. Journal of Textile Research, 2014, 35(3): 158-164.
李文羽, 程隆棣. 基于机器视觉和图像处理的织物疵点检测研究新进展[J]. 纺织学报, 2014, 35(3): 158-164.

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

引用该论文

Tan Yongqian,Zeng Fanju,Wu Weiwei,Zhang Hongyun. Texture Transmission Image Stylized Processing Based on Non-Linear Filtering and Edge Detection[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061012

谭永前,曾凡菊,吴位巍,张鸿筠. 基于非线性滤波和边缘检测的纹理传输图像风格化处理[J]. 激光与光电子学进展, 2018, 55(6): 061012

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