BP和RBF神经网络在字母识别中的比较  

Comparison with BP and RBF neural network used in English Letters Recognition

作　　者：高富强[1] 邹恒[2] 秦昌硕[2] 须民健[2] 杨勇[2] 

机构地区：[1]重庆大学ICT研究中心,重庆400030 [2]重庆大学自动化学院,重庆400030

出　　处：《重庆工学院学报（自然科学版）》2009年第9期77-80,共4页Journal of Chongqing Institute of Technology

基　　金：国家"863"高技术研究发展计划资助项目(2006AA04Z104)

摘　　要：将BP和RBF2种神经网络应用于英文字母识别,为2种网络建立识别模型.利用标准字符库进行测试,并在测试中加入干扰,进行仿真实验,观察这2种网络的泛化能力以及识别准确性,比较这2种网络及其改进方案,提出这2种改进方案中分别需要注意的地方.指出当用于字母识别时,RBF网络的性能优于BP网络及其改进型算法.BP and RBF in pattern recognition are two most widely used kinds of neural networks. In this article, a recognition model for them is established and is tested with standard English letters. Interference is put in the test, these two kinds of neural networks with their ability of recognition are compared, and some places that should be given special attention are put forward. It is pointed out that when used in letters reeognition, the performance of RBF network is superior to BP network and its improved algorithm

关 键 词：BP神经网络 RBF神经网络 模式识别 英文字母识别 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]