三维模型特征识别中的分割与编码算法

Segmentation and Coding Algorithm in 3D Feature Recognition

三维模型特征识别是CIMS中的关键技术之一 ,用神经网络法解决三维模型的特征识别问题 ,具有鲁棒性、多重解释、根据例子学习、识别速度较快等许多优势。基于凹凸变化产生特征的思想 ,根据底面、凹点、凹边等线索 ,对三维模型进行合理的分割 ,找出三维模型特征可能存在的区域 ,并对该特征区域进行编码 ,将三维模型的拓扑信息、几何信息转化为神经网络能够处理的矢量数据。最后 ,再利用人工神经网络的学习与识别能力识别出模型的特征。

The recognition of the feature of 3D models is one of the key technologies in the CIMS engineering, and the algorithm using neural networks can solve this problem with many advantages, such as fast calculating, learning from examples, etc. This paper designed a method to decompose the model into several parts with the hints from bottom faces, concave vertexes and concave edges, etc. And also a coding algorithm based on the face relation matrix(FRM) was given to translate the topology data of a part into the vector, which can be proceeded by the neural networks. Finally, with the help of a learnable artificial neural networks, most of the 3D features of a model could be recognized.