基于知识库的颅骨特征点标定

Skull feature point calibration based on knowledge database

提出一种基于知识库的三维颅骨特征点标定方法。首先,对于待标定颅骨,在知识库中找到与其形态最为相似的模板颅骨。然后,在法兰克福坐标系下,将模板颅骨上的标准特征点映射到待标定颅骨上。最后,利用K-D树对最终特征点的位置优化、精确。实验证明,当k值在颅骨模型顶点个数的1.5%~2.1%时,标定效果较好。

A 3D skull feature point calibration method based on knowledge base is proposed in this paper.Firstly,for a calibrated skull,the most similar template skull is retrieved in the knowledge database. Then,the standard feature points on the template skull are mapped to the specific position of the skull to be measured under the Frankfurt coordinate system. Finally,K-D tree is used to modify and optimize the location of standard points. The experimental results that when k value accounts for 1. 5% ～ 2. 1% of vertex number of skull model,the characteristic point calibration effect is better.