| 一种基于MATLAB的手写字母的神经网络识别方法 |
| |
| 引用本文： | 邓铭辉,孙枫,张志.一种基于MATLAB的手写字母的神经网络识别方法[J].应用科技,2001,28(10):28-30. |
| |
| 作者姓名： | 邓铭辉 孙枫 张志 |
| |
| 作者单位： | 哈尔滨工程大学自动化学院黑龙江哈尔滨 150001 |
| |
| 摘 要： | 利用前向多层神经网络的反向传播算法，即BP算法，采用MATLAB软件构建用于特征识别的两层前向神经网络，将已知字母经图象处理后对BP网络进行训练，此BP神经网络可以成功地识别A－Z26个手写英文字母。
|
| 关 键 词： | MATLAB 前向神经网络 反向传播算法 图象处理 灰度矩阵 手写字母 模式识别 |
| 文章编号： | 1009-671(2001)10-0028-03 |
| 修稿时间： | 2001年4月4日 |
A Kind of Neural Network Method for Distinguishing Written English Letters |
| |
| DENG Ming_hui,SUN Feng,ZHANG Zhi.A Kind of Neural Network Method for Distinguishing Written English Letters[J].Applied Science and Technology,2001,28(10):28-30. |
| |
| Authors: | DENG Ming_hui SUN Feng ZHANG Zhi |
| |
| Abstract: | In this paper, the back propagation algorithm of a feedforward neural network was used with MATLAB, and a multilayer feedforward neural network was founded for the character distinguishing. After image processing, the known example English letters were made to train the BP neural network. So the BP neural network would be able to distinguish 26 written English letters from A to Z . |
| |
| Keywords: | MATLAB feedforward neural network back propagation algorithm image processing brightness matrix |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
