辽宁石油化工大学学报

辽宁石油化工大学学报 ›› 2010, Vol. 30 ›› Issue (1): 76-80.DOI: 10.3696/j.issn.1672-6952.2010.01.021

• 计算机与自动化 • 上一篇    下一篇

一种新的纹理合成算法

郭小明   

  1. 辽宁石油化工大学理学院,辽宁抚顺113001
  • 收稿日期:2009-07-25 出版日期:2010-03-25 发布日期:2017-07-05
  • 作者简介:郭小明(1980-),女,辽宁盖州市,硕士。
  • 基金资助:
    :辽宁省教育厅高校科研项目(2004F100);辽宁石
    油化工大学重点学科建设资助项目(K200409)。

A Novel Layered Texture Synthesis Algorithm

 

GUO Xiao-ming
  

  1. School of Sciences, Liaoning Shihua University,Fushun Liaoning 113001, P.R.China
  • Received:2009-07-25 Published:2010-03-25 Online:2017-07-05

摘要: 现有纹理合成算法并不能保证合成物体的完整性,也不能使其分布与样本纹理保持一致。提出了一
种分层纹理合成算法。首先,采用归一化图像分割算法提取样本纹理中的视觉显著性前景物体,继而采用图像修复
算法修复背景,然后统计前景物体在样本纹理中的分布共生矩阵,以此作为约束,在背景图像上确定前景物体的分
布位置。实验结果表明,不仅可以对前景物体独立进行各种变换,得到任意分布的合成纹理,而且可以保证前景物
体的完整性。

关键词: 纹理合成 , 图像分割 , 分布

Abstract:  

Current texture synthesis algorithms can neither preserve the integrity of the salient object, nor keep the same distribution of the salient object in the synthesized textures as that in the source texture. A novel layered texture synthesis algorithm was proposed. Firstly, the salient objects were extracted by adopting the normalized cut image segmentation method. Then an image imprinting algorithm was applied to fill the holes caused by salient object extraction in the background to generate a completed background sample, with which we can synthesis the full background image of the target texture. The experimental result shows that this algorithm can not only get the distribution of the salient object in the synthesized textures but also preserve the integrity of the salient object.

Key words: Texture synthesis , Image segmentation ,  , Distribution

引用本文

郭小明. 一种新的纹理合成算法[J]. 辽宁石油化工大学学报, 2010, 30(1): 76-80.

GUO Xiao-ming. A Novel Layered Texture Synthesis Algorithm[J]. Journal of Liaoning Petrochemical University, 2010, 30(1): 76-80.

使用本文

0
    /   /   推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal.lnpu.edu.cn/CN/10.3696/j.issn.1672-6952.2010.01.021

               http://journal.lnpu.edu.cn/CN/Y2010/V30/I1/76