二维图像的光亮度重构实体几何模型的神经网络法  

A New Approach to Construct Solid Geometry Model From the 2-dimensional Shape Based on Neural Networks

作　　者：鄢腊梅[1] 袁友伟[2] 

机构地区：[1]株洲工学院机械系,株洲412008 [2]株洲工学院计算机系,株洲412008

出　　处：《机械设计与研究》2003年第6期36-38,共3页Machine Design And Research

基　　金：国家自然科学基金资助项目 ( 5 0 2 740 80 ) ;湖南省教育厅重点学科建设项目 ( 0 2 0 64 3 )。

摘　　要：三维表面重建技术具有广泛的应用前景 ,由二维图像的光亮度重构实体几何模型是工业制造中迫切需要研究的课题之一。本文给出了一种基于BP神经网络的新型反射模型 ,用于三维实体几何模型的恢复与重建 ,它是基于兰伯特 (Lambertian)反射模型的改进算法。这一造型手段可用于CAD/CAE/CAM系统中 ,使得重建出的三维模型可以参与造型系统实体的基本运算和操作 ,共同推动CAD/CAE/CAM在制造业信息化领域的技术进步。从实例表明该算法较传统的算法更快和更精确。D shape reconstruction has numerous applications,and the approach to construct solid geometry model from 2 dimensional shape are widely studied.The algorithm of shape from shading based on BP neural networks is proposed,which is based on Lambertian reflection model.The method has a good application to the CAD/CAE/CAM system;and it is also easier to be operated and realized by a computer.The method will also promote the CAD/CAE/CAE progress in the feild of manufactuing information. In comparison with the traditional methods,examples show that the algorithm is verified to be accurate and applicable.

关 键 词：实体几何模型 表面重建 神经网络 算法 光亮度 CAD CAE CAM 制造业 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]