首页 | 本学科首页   官方微博 | 高级检索  
     

基于迭代最近点的B样条曲线拟合方法研究
引用本文:肖轶军,丁明跃,彭嘉雄.基于迭代最近点的B样条曲线拟合方法研究[J].中国图象图形学报,2000,5(7):585-588.
作者姓名:肖轶军  丁明跃  彭嘉雄
作者单位:[1]华中理工大学图象识别与人工智能研究所 [2]中国科学院自动化所模式识别国家重点实验室
基金项目:国家自然科学基金!( 69775 0 0 5 ),国家教委跨世纪优秀人才基金
摘    要:曲线拟合在图象处理、逆向工程应用等领域中有着重要意义。由于对于B样条参数曲线拟合,数据点的参数化直接影响着拟合的精度,因此提出了一种基于迭代最近点的方法来优化修正数据点的参数,并且证明了应用该方法进行曲线拟合具有局部收敛性。通过实验分析,验证了方法的正确性和鲁棒性。

关 键 词:B样条  曲线拟合  迭代最近点  计算机图象处理
收稿时间:1999/6/17 0:00:00
修稿时间:1999-06-17

ICP-Based B-spline Curve Fitting
XIAO Yi-jun,DING Ming-yue and PENG Jia-xiong.ICP-Based B-spline Curve Fitting[J].Journal of Image and Graphics,2000,5(7):585-588.
Authors:XIAO Yi-jun  DING Ming-yue and PENG Jia-xiong
Affiliation:Institute for Pattern Recognition&Artificial Intelligence,Huazhong University of Science&Technology,Wuhan430074 State Education Commission Laboratory for Image Processing and Intelligent Control; ;National Laboratory of Pattern Recognition,Institute of Au;Institute for Pattern Recognition&Artificial Intelligence,Huazhong University of Science&Technology,Wuhan430074 State Education Commission Laboratory for Image Processing and Intelligent Control; ;National Laboratory of Pattern Recognition,Institute of Au;Institute for Pattern Recognition&Artificial Intelligence,Huazhong University of Science&Technology,Wuhan430074 State Education Commission Laboratory for Image Processing and Intelligent Control; ;National Laboratory of Pattern Recognition,Institute of Au
Abstract:Curve fitting has been applied in many fields such as image pr ocessing and reverse engineering. In B-spline curve fitting, the parametrizatio n of data points is a key problem. In this paper, an ICP-based algorithm to rec tify the parameter values of data points is presented. The ICP algorithm always converges monotonically to the nearest local minimum. The proof of the convergen ce theorem is given. The analysis of experimental results demonstrates the valid ity and robustness of our algorithm.
Keywords:B-spline  Curve fitting  ICP(Iterative Closest Point)  Parame ter rectification
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号