摘要
将径向基函数网络与隐式曲线构造原理相结合,提出了构造隐式曲线的新方法,即首先由约束点构造神经网络的输入与输出,把描述物体边界曲线的隐式函数转化为显式函数,然后用径向基函数网络对此显式函数进行逼近,最后由神经网络的仿真曲面得到物体边界的拟合曲线.实验表明,基于径向基函数网络的隐式曲线具有很强的物体边界描述能力和缺损修复能力.
A new method for closed curve construction is introduced, which is based on the combination of RBF (radial basis function) neural network and the principle of implicit curve construction. The algorithm, firstly, constructs the input and output of the RBF neural network from the constraint points, secondly changes the implicit function that represents object boundary into explicit function, thirdly uses RBF neural network to fit the curve of the explicit function, and finally obtains the fitting curves that represent the object boundary from the simulation surface. The main difference between the new method and other methods is that it is unnecessary for the new method to minimize the sum of the squares of the Euclidean distance or to solve linear system. The method not only has better results than the method based on BP neural network, and also has some merit of locality that other methods do not have. It has good numerical stability and robustness in dealing with noisy or missing data. Experimental results are given to verify the effectiveness of recovering incomplete images and object boundary reconstruction.
出处
《计算机研究与发展》
EI
CSCD
北大核心
2005年第4期599-603,共5页
Journal of Computer Research and Development
基金
国家"九七三"重点基础研究发展规划基金项目(G1999032805)
关键词
隐式曲线
拟合
径向基函数网络
物体边界描述
implicit curve
fitting
radial basis function network
object boundary representation
