二维非规则碎片匹配的算法

被引:29
作者
朱延娟 [1 ]
周来水 [2 ]
刘毅 [1 ]
机构
[1] 同济大学航空航天与力学学院
[2] 南京航空航天大学CAD/CAM工程研究中心
关键词
碎片匹配; 轮廓; 拼合; 曲率; 特征点;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
提出了一种基于曲率相似性的二维碎片轮廓匹配算法。该算法根据碎片轮廓上各点的曲率值来确定轮廓上的特征点,按照特征点对轮廓进行分段,将二维碎片的匹配简化为特征段的相似性度量与可匹配性验证。对可匹配的轮廓段进行欧氏变换以拼合两个轮廓曲线,自动地检测在当前变换下两个轮廓是否有重叠情况存在。没有重叠的两个轮廓组合起来更新为一个新的轮廓,进行再匹配直至重建过程完成。实例表明,算法是有效、稳定的。
引用
收藏
页码:7 / 9
页数:3
相关论文
共 6 条
[1]  
A Multi-scale Method for the Reassembly of Two-dimensional Fragmented Objects. Leit?o H C G,Stolfi J. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2002
[2]  
A Theory of Multiscale,Curvature-based Shape Representation for Planar Curves. Mokhtarian F,Mackworth A K. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1992
[3]  
Comments on the localization performance measure and optimal edge detection. Boyer K L,Sarkar S. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1994
[4]  
Apictorial Jigsaw Puzzles:The Computer Solution of a Problem in Pattern Recognition. Freeman H,Gardner L. IEEE Trans.on Electronic Computers . 1964
[5]  
On Solving 2D and 3D Puzzles Using Curve Matching. Kong Weixin,Kimia B B. Proc.of the IEEE Conference on Computer Vision and Pattern Recognition . 2001
[6]  
A Global Approach to Automatic Solution of Jigsaw Puzzles. Goldberg D,Malon C,Bern M W. Proc.of Symposium on Computational Geometry . 2002