›› 2013, Vol. 42 ›› Issue (4): 0-0.

• 学术论文 •    

面状要素的多层次骨架线提取

刘小凤1,吴艳兰1,胡海2   

  1. 1. 武汉大学
    2. 武汉大学资源与环境学院
  • 收稿日期:2012-07-16 修回日期:2012-11-17 出版日期:2013-08-20 发布日期:2014-01-23
  • 通讯作者: 刘小凤 E-mail:lxf_whu@163.com
  • 基金资助:
    椭球上海洋划界中的比例线法技术研究

A method of extracting Multiscale skeletons for polygonal shapes

  • Received:2012-07-16 Revised:2012-11-17 Online:2013-08-20 Published:2014-01-23

摘要: 多边形的骨架线是对其形态的准确描述,多尺度的骨架线表达在图形分析如多边形的形态恢复和多边形的模式识别等方面具有重要作用。利用双缓冲区变换、障碍距离变换和Voronoi图技术,本文提出一种新的多边形多层次骨架线提取方法,并且,利用复杂湖泊多边形、简单多边形、含岛洞多边形、噪声边缘多边形等不同形状的多边形测试和比较了该方法提取的骨架线的连通性、拓扑一致性和对图形旋转的灵敏性等。实验结果表明,本文方法在上述特性上优于现有算法。

关键词: 障碍距离变换, 缓冲区变换, 多层次骨架, Voronoi图

Abstract: Polygon skeleton is generally recognized as a good shape descriptor. The multiscale representation of polygon skeletons makes it convenient for image analyzing, such as polygon shape recovering, pattern recognition etc. This paper presented a new method to extract multiscale skeletons basing on double buffering transforming, obstacle distance transforming and Voronoi diagram. We tested our method by extracting various skeletons from polygons in different shapes and compared the skeletons qualities from the following indexes, connectivity, topological consistency, and graphics rotating sensitivity. These experimental polygons include complex lake polygon, simple polygon, polygons with holes and noisy polygons. Result shows that according to the above criteria, our method outperforms existing methods to a certain extent.

Key words: Obstacle distance transform, double buffering transform, Multiscale Skeleton, Voronoi Digram

中图分类号: