|
|||||
|
|
| 基于BP神经网络的字符识别系统 | |
| 引用本文： | 张可,张高燕,吴苏,范海菊.基于BP神经网络的字符识别系统[J].计算机与现代化,2009(1). |
| 作者姓名： | 张可 张高燕 吴苏 范海菊 |
| 作者单位： | 1. 南京航空航天大学信息科学与技术学院,江苏,南京,210016 2. 北京师范大学信息科学与技术学院,北京,100875 3. 哈尔滨工程大学计算机科学与技术学院,黑龙江,哈尔滨,150001 4. 河南师范大学计算机与信息技术学院,河南,新乡,453007 |
| 摘 要： | 基于BP神经网络设计了一个字符识别系统.首先,对字符图像进行二值化处理,构造输入向量矩阵.其次,通过选取初始权值、隐层节点数和权值学习算法,创建BP神经网络,对样本数据进行训练,之后对加有噪声的样本再次进行训练,以提高网络的鲁棒性.最后进行仿真测试并制作图形用户界面GUI来模拟与演示该系统.仿真结果显示,该BP网络对噪声系数小于0.8的字符识别率可达95%,且网络训练时间可接受. |
| 关 键 词： | BP神经网络 字符识别 鲁棒性 |
System of Character Recognition Based on Back-propagation Neural Network |
|
| ZHANG Ke,ZHANG Gao-yan,WU Su,FAN Hai-ju.System of Character Recognition Based on Back-propagation Neural Network[J].Computer and Modernization,2009(1). | |
| Authors: | ZHANG Ke ZHANG Gao-yan WU Su FAN Hai-ju |
| Affiliation: | 1.College of Information Science and Technology;Nanjing University of Aeronautics and Astronautics;Nanjing 210016;China;2.College of Information Science and Technology;Beijing Normal University;Beijing 100875;3.College of Computer Science and Technology;Harbin Engineering University;Harbin 150001;4.College of Computer and Information Technology;Henan Normal University;Xinxiang 453007;China |
| Abstract: | This article designs a character recognition system based on the Back-Propagation neural network.First,the character image is processed in binary to construct the input vector matrix.Second,by choosing the initial weight,the number of hide nodes and the learning algorithm of weight,a perfect BP neural network is created.And then the network carries on the training to the sample data and afterwards to the sample with noise once more,to enhance the network robustness.Finally,it carries on the simulation test ... |
| Keywords: | GUI |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |