基于像素自适应邻域的纹理合成方法

doi:10.12068/j.issn.1005-3026.2014.09.010

东北大学学报:自然科学版 ›› 2014, Vol. 35 ›› Issue (9): 1257-1260.DOI: 10.12068/j.issn.1005-3026.2014.09.010

基于像素自适应邻域的纹理合成方法

王展，颜云辉，宋克臣

(东北大学机械工程与自动化学院，辽宁沈阳110819)

收稿日期:2013-10-21 修回日期:2013-10-21 出版日期:2014-09-15 发布日期:2014-04-11
通讯作者: 王展
作者简介:王展(1984-)，男，辽宁鞍山人，东北大学博士研究生；颜云辉(1960-)，男，江苏丹阳人，东北大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目(51374063)；中央高校基本科研业务费专项资金资助项目(N120603003).

Texture Synthesis Method Based on Pixel Adaptive Neighborhood

WANG Zhan， YAN Yunhui， SONG Kechen

School of Mechanical Engineering & Automation， Northeastern University， Shenyang 110819， China.

Received:2013-10-21 Revised:2013-10-21 Online:2014-09-15 Published:2014-04-11
Contact: WANG Zhan
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对传统像素点的纹理合成方法普遍存在对纹理样本适用范围比较窄的问题，提出了一种可以自动确定最佳匹配像素邻域大小的纹理合成方法.首先，利用方块编码原理提取样本纹理元，通过纹理元来确定最佳匹配像素邻域；然后，在像素匹配阶段，对像素匹配准则进行改进.通过比较样本像素和目标像素邻域的均值和方差来确定邻域的相似度，最终选择最优的合成像素.对比实验表明，该方法不仅有良好的合成效果，而且具有较广的适用范围，可以作为一种通用性的纹理合成方法.

关键词: 纹理合成, 纹理元, 方块编码, 邻域匹配, 像素邻域

Abstract: A novel method that can automatically confirm the best neighborhood size of pixel matching was proposed to improve the narrow application range of traditional pixelbased texture synthesis. Firstly， texton was extracted using block truncation coding， and the best neighborhood size of pixel matching was confirmed by the texton. Then， the norm of pixel matching was improved in the matching stage. By comparing the mean values and variance of sample pixels and target pixels， neighborhood similarity and optimal pixel can be deternined. The results show that the proposed method can generate good synthesis and has a wide application range， and thus can be a universal texture synthesis technology.

Key words: texture synthesis, texton, block truncation coding, neighborhood matching, pixel neighborhood

中图分类号:

TP391

王展，颜云辉，宋克臣. 基于像素自适应邻域的纹理合成方法[J]. 东北大学学报:自然科学版, 2014, 35(9): 1257-1260.

WANG Zhan， YAN Yunhui， SONG Kechen. Texture Synthesis Method Based on Pixel Adaptive Neighborhood[J]. Journal of Northeastern University Natural Science, 2014, 35(9): 1257-1260.

参考文献

[1] Efros A A，Leung T K.Texture synthesis by nonparametric sampling［C］//The Proceedings of the Seventh IEEE International Conference on Computer Vision.Los Alamitos:IEEE Press，1999:1033/1038.
[2] Wei L Y，Levoy M.Fast texture synthesis using treestructured vector quantization［C］//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM，2000:479/488.
[3] Ashikhmin M.Synthesizing natural textures［C］//Proceedings of the 2001 Symposium on Interactive 3D graphics.New York:ACM，2001:217/226.
[4] 陈昕，王文成.基于复用计算的大纹理实时合成［J］.计算机学报，2010，33(4):768/775.(Chen Xi，Wang Wencheng.Reusing partially synthesized textures for realtime synthesis of large textures［J］.Chinese Journal of Computers，2010，33(4):768/775.)
[5] Lefebvre S，Hoppe H.Parallel controllable texture synthesis［J］.ACM Transactions on Graphics，2005，24(3):777/786.
[6] Tong X，Zhang J D，Liu L G，et al.Synthesis of bidirectional texture functions on arbitrary surfaces［J］.ACM Transactions on Graphics，2002，21(3):665/672.
[7] Hertzmann A，Jacobs C E，Oliver N，et al.Image analogies［C］//Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM，2001:327/340.
[8] 王祖海，陶兢喆，宋传鸣.并行波峰模式的规则块拼接纹理合成调度［J］.计算机辅助设计图形学学报，2013，25(2):248/257.(Wang Zuhai，Tao Jingzhe，Song Chuanming.Task schedule for regular patchbased texture syhthesis in the parallel wavefront pattern［J］.Journal of ComputerAided Design & Computer Graphics，2013，25(2):248/257.)
[9] Takahashi N，Iwasaki I，Kunieda T，et al.Image retrieval using spatial intensity features［J］.Signal Processing:Image Communication，2000，16(1):45/57.

基于像素自适应邻域的纹理合成方法

Texture Synthesis Method Based on Pixel Adaptive Neighborhood

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价