基于径向基函数网络的显微结构下目标三维测量.pdfVIP

基于径向基函数网络的显微结构下目标三维测量* 1 2 1 石晓龙 许志榜 许进 (1 华中科技大学 控制科学与工程系, 湖北 武汉 430074; 2 华东交通大学电气与电子工程学院, 江西 南昌 330013） 摘要：本文基于对显微结构下目标三维特征分析，结合神经网络算法，提出了基于神经网络 算法的目标三维测量。通过径向基函数网络对实现了对目标图像的小波特征提取与测量。将 对信号的小波包分析与 RBF 网络的结合，以较小的计算代价实现了对目标图像的三维特征 的提取与测量。 关键词：三维测量，特征提取，RBF 网络 中图分类号：TP75 文献标识码： A Application of RBF Networks for 3-Dimension Measurement under Microscope 1 2 1 Shi Xiaolong , Xu Zhibang , Xu Jin (1 Dept. of Control Sci. Eng.; Huazhong Univ. of Sci. Tech.; Wuhan; China; 2 Dept. of Electrical and Electronic Engineering; East China Jiaotong University; Nanchang; China） Abstract ：This article is concerned with the research on the 3-Dimension measurement of objects under microscope, which is essential to the detection and manipulation problems in Micro-flow System. The author proposed a new method to detect the 3-Dimension information under microscope. By introducing neural network and wavelet theory, the calibration procedure can be implemented automatically by neural network. After the calibration procedure, the relationship between micrographic images and lengthwise distance of the object under microscope is mapped as the weight point of the neural network, and the measurement procedure can be quickly implement automatically with an input image of the object under microscope. Keywords：3-Dimension measurement Feature extraction RBF Network Shi Xiaolong Post Doctor; Department of Control Science and Engineering, Huazhong University of Science Technology, Hubei Prov. Wuhan 430074, P. R. China. 1. 引言 通过的对显微结构下目标图像的三维特征分析，我们可以得到一系列可以表征目标轴向 距离的二维图像特征[1] 。然而这些目标平面图像的三维相关特征与目标轴向距离的关系