摘要
通过把BP神经网络与隐式曲面构造原理相结合,提出构造隐式曲面的新方法.用约束点来描述、控制曲面形状,构造BP网的输入与输出,通过智能学习、仿真模拟,最后从仿真超曲面抽取出的零等值面就是隐式曲面.同时,从理论上证明了此方法所构造的隐式曲面具有任意精度.实验表明该方法对约束点的个数、误差、内外点与边点的距离等不敏感,表现出很好的稳定性与可操作性.该构造方法不仅可用于构造隐式曲面,而且在图形理解、数据分类等领域也具有良好的应用前景.
Neural networks, combined with implicit polynomials, can be employed to represent 3D surfaces which are described by the zero-set of a neural network. First, an explicit function is constructed based on the implicit function. Then the explicit function is approximated by a BP neural network. Finally, the zeroset of the neural network which is the implicit surface is extracted from the simulation surface. The method is not sensitive to the error, the number of the constraint points, and the distance between the boundary points and inner/extern points. Experimental results are given to verify the effectiveness of surface reconstruction.
出处
《计算机研究与发展》
EI
CSCD
北大核心
2007年第3期467-472,共6页
Journal of Computer Research and Development
基金
江苏省普通高校自然科学研究计划基金项目(05KJB520032)
关键词
隐式曲面
BP神经网络
曲面重建
拟合
implicit surface
BP neural networks
surface reconstruction
fitting