期刊文献+

基于生长原理的磨牙修复体面特征区域识别方法

GROWTH PRINCIPLE BASED RECOGNITION METHOD FOR OCCLUSAL SURFACE FEATURE REGIONS OF MOLAR RESTORATION
下载PDF
导出
摘要 为精确加工出牙齿修复体的面,以保证其咬合功能,可将修复体的面划分为一系列"沟、窝、嵴、包"型的特征区域分别进行加工。基于生长原理,提出一种在磨牙修复体的STL模型上进行面特征区域识别的方法。对于STL模型上的某一局部面域,首先根据法矢的分布情况,进行沟(嵴)与窝(包)的判别。对于沟(嵴)区域,先沿法矢变化最小的方向生长出沟底线(嵴顶线),再利用"等夹角环"逐层向外生长形成边界。对于窝(包)区域,直接利用"等夹角环"逐层向外生长确定其边界。在标准磨牙STL模型中进行了特征区域的识别。实例证明,所提出的基于生长原理的识别方法是一种可行的方法。 In order to make up the occlusal surface of a molar restoration accurately so that it can occlude well,the occlusal surface of restoration may probably be partitioned into some feature regions such as gouge, socket, ridge and bulge and then to make each one respectively. Based on the principle of natural growth, in this paper we present an approach of feature regions recognition in the STL model of a molar restoration. As to a local region in the STL model, it is distinguished whether it's a gouge( or ridge) or a socket( or bugle) according to distribution of normal vectors. As to a gouge( or ridge), the bottom (or top) line is established along the direction on which normal vectors vary minimally, and its edge can be obtained by extending outward ring-by-ring using "equal angle ring". As to a socket( or bulge) ,its edge can be obtained by directly extending outward ring-by ring using "equal angle ring". Feature regions recognition was done in standard molar restoration STL model. The instance shows that this growth principle based recognition method is a feasible one.
出处 《计算机应用与软件》 CSCD 2010年第3期87-89,123,共4页 Computer Applications and Software
基金 江苏省自然科学基金面上项目(BK2006060)
关键词 [牙合]面 特征识别 区域分割 生长 等夹角环 Occlusal surface Feature recognition Region segmentation Growth Equal angle ring
  • 相关文献

参考文献14

二级参考文献74

  • 1芮挺,沈春林,丁健,张金林.基于主分量分析的手写数字字符识别[J].小型微型计算机系统,2005,26(2):289-292. 被引量:22
  • 2祝国旺,孙健,周济,余俊.CAD/CAM中的特征技术综述[J].计算机应用,1994,14(4):8-12. 被引量:13
  • 3孙鑫,刘本永.基于局部本征谱的人脸识别[J].电子科技大学学报,2005,34(4):493-496. 被引量:1
  • 4张保轩,房世晖.基于外形特征的手写体数字识别[J].山东通信技术,1995(1):28-31. 被引量:1
  • 5Suen C Y, Nadal C, Legault Retal. Computer Recognition of Unconstrained Handwritten Numerals [P].Proc of the IEEE, 1992,80(7) :1162-1180.
  • 6Harvey N R, Theiler J, Brumby S P, et al. Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction [J]. IEEE, 2002,40(2):393 - 404.
  • 7Wang X, Ding X, Liu C. A gray-scale image based character recognition algorithm to low-quality and low-resolution images [J]. Proceedings of SPIE, 2001, 24- 25 (4307):315 - 322.
  • 8Besl P J ,Jain R C. Segmentation through Variable-order Surface Fitting. IEEE Trans Pattern Anal,1998,10(2) :167-192.
  • 9Sarkar B, Meng C H. Smooth Surface Approximation and Reverse Engineering. Computer Aided Design,1991,23(9) : 623-628.
  • 10Lee Y, Park S, Jun Y,et al. A Robust Approach to Edge Detection of Scanned Point Data. Int. J. Adv.Manuf. Techmol. , 2004,23 : 263 -271.

共引文献159

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部