辽宁石油化工大学学报

辽宁石油化工大学学报 ›› 2008, Vol. 28 ›› Issue (1): 52-54.

• 计算机与自动化 • 上一篇    下一篇

基于改进BP神经网络的手写邮政编码识别

顾妍午李 平*, 陶文华田绍宽   

  1. 辽宁石油化工大学信息与控制工程学院, 辽宁抚顺 113001
  • 收稿日期:2007-11-02 出版日期:2008-03-20 发布日期:2017-07-22

Handwriting Postal Codes Recognition Based on Improved BP Neural Network

GU Yan-wu, LI Ping*, TAO Wen-hua, TIAN Shao-kuan   

  1. School of Information and Control Engineering, Liaoning University of Petroleum & Chemical Technology,  Fushun Liaoning 113001,P.R.China
  • Received:2007-11-02 Published:2008-03-20 Online:2017-07-22

摘要: 为解决手写邮政编码识别困难的问题,引入改进的粗网格特征提取方法,对神经网络的网络输入进行简化,并且采用基于LM算法的BP神经网络来进行网络学习。LM算法是一种改进的高斯-牛顿算法,此算法通过简化的网络输入,进一步提高了网络学习的精度、稳定度和学习速度。仿真结果验证了此算法在手写邮政编码识别中的有效性。

关键词: BP神经网络, LM算法, 特征提取, 手写邮政编码

Abstract: In order to solve the difficult problem of handwriting postal codes recognition, an improved coarse grid feature extraction approach which simplifies network input of the neural network was introduced. BP neural network based on LM algorithm for network studying was adopted. LM algorithm is an improved Gauss-Newton algorithm. The improved algorithm further enhances precision, stability and studying speed of the network studying through the simplification of the network input. The simulation results show that the algorithm is effective on the handwriting postal codes recognition.

Key words: BP neural network, LM algorithm, Feature extraction, Handwriting postal codes 

引用本文

顾妍午, 李 平, 陶文华, 田绍宽. 基于改进BP神经网络的手写邮政编码识别[J]. 辽宁石油化工大学学报, 2008, 28(1): 52-54.

GU Yan-wu, LI Ping, TAO Wen-hua, TIAN Shao-kuan. Handwriting Postal Codes Recognition Based on Improved BP Neural Network[J]. Journal of Liaoning Petrochemical University, 2008, 28(1): 52-54.

使用本文

0
    /   /   推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://journal.lnpu.edu.cn/CN/

               https://journal.lnpu.edu.cn/CN/Y2008/V28/I1/52