径向基函数网络在形状识别中的应用  

Application of radial basis function neural network in shape recognition

作　　者：胡勇[1] 赵琴[1] 高隽[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2003年第1期27-30,共4页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(60175011);安徽省自然科学基金资助项目(01042301);教育部优秀青年教师资助项目

摘　　要：径向基函数神经网络是一种应用相当广泛的神经网络。文章对径向基函数网络的基本原理、网络结构和学习算法进行了介绍,根据径向基函数网络的特点将其应用到形状识别领域,并通过MATLAB平台编程实现其算法。实验结果证明网络初始中心和样本数目的选择对识别结果影响较大;在初始中心选择相同的情况下,实验样本数目越多,识别结果越好;在达到一定数目后,识别正确率趋于稳定。Radial basis function neural network(RBFNN) is one of the neural networks used widely. In this paper, the principle,structure and training algorithm of RBFNN are introduced. Then RBFNN is applied to the shape recognition system of traffic signs, and the algorithm is realized in MATLAB environment. The result of the experiment proves that the original center and the number of samples have a considerable effect on the recognition outcome. When the original center is the same one,the more the number of samples,the better the recognition outcome,and the ratio of correct recognition becomes steady as the samples reach a proper number.

关 键 词：径向基函数神经网络 形状识别 学习算法 计算机视觉 自动识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]