摘要
提取干涉条纹的中心是干涉测量的关键环节,文中提出了一种基于细胞神经网络(CNN)提取干涉条纹中心的新方法。CNN是一种实时处理信号的大规模非线性模拟电路,同时它的局部联接特点使其适用于超大规模集成电路的实现。CNN具有并行运算的能力,可消除传统串行算法复杂性高、不能实时处理的缺点。对该方法进行了分析,给出了实例的仿真结果,证明该方法能快速准确地提取干涉条纹的中心,提高了干涉条纹的判别精度,从而增加了实验中干涉条纹处理的直观性和实时性。
It is very important that extracting the center of interference - stripes in the interference measurement. A new method to extract the center of interference - stripes using cellular neural networks （CNN） is described. As a large - scale nonlinear analog circuit, the CNN is suitable for real- time signal and image processing. The CNN can be used for high- speed parallel computation and is easy to be translated into a VLSI implementation. A two - dimensional CNN that performs an algorithm to extracting the center of interference - stripes is proposed. Some practical results are presented and briefly discussed, which demonstrates the successful operation of the proposed algorithm.
出处
《计量学报》
EI
CSCD
北大核心
2006年第2期117-120,共4页
Acta Metrologica Sinica
关键词
计量学
细胞神经网络
干涉条纹
图像处理
Metrology
Cellular neural networks （CNN）
Interference - stripes
Image process
