| 基于BP神经网络的手写数字识别 |
| |
| 引用本文： | 杨勇,谢刚生.基于BP神经网络的手写数字识别[J].华东地质学院学报,2003,26(4):383-386. |
| |
| 作者姓名： | 杨勇 谢刚生 |
| |
| 作者单位： | 东华理工学院，江西抚州344000 |
| |
| 摘 要： | 介绍了光学字符识别的几种方法以及神经网络的特点，神经网络技术能够解决传统OCR方法所不能解决的问题，同时指出了手写数字识别存在的困难，论证了利用神经网络技术解决这种困难的可能性。本文实现了通过一个含有1个隐藏层的BP网络来识别手写数字，并取得了良好效果，论证了这种技术用于手写数字识别的可行性。
|
| 关 键 词： | 神经网络 模式识别 手写数字 |
| 文章编号： | 1000-2251(2003)04-383-04 |
| 修稿时间： | 2003年4月24日 |
Handwritten Digit Recognition Based on BP Neural Network |
| |
| YANG Yong,XIE Gang-Sheng.Handwritten Digit Recognition Based on BP Neural Network[J].Journal of East China Geological Institute,2003,26(4):383-386. |
| |
| Authors: | YANG Yong XIE Gang-Sheng |
| |
| Abstract: | Some methods of OCR and feature of Neural Networks(NN) are introduced, and NN technique can solve problems which can't be solved by traditional OCR methods. At the same time, the exist difficult in handwritten digit recognition are pointed, and the possibility of solving the problems using NN technique is proved. NN approach for handwritten digit recognition being proposed in this paper and a one hidden layer BP networks being constructed, more effect are received and the feasibility is proved. |
| |
| Keywords: | artificial neural network(ANN) pattern recognition handwritten digit |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
