首页 | 本学科首页   官方微博 | 高级检索  
     检索      

BP网络在手写体数字识别中的应用
引用本文:赵伟,王俊宏,李娟,卢照棠.BP网络在手写体数字识别中的应用[J].林业劳动安全,2005,18(2):38-42,44.
作者姓名:赵伟  王俊宏  李娟  卢照棠
作者单位:1. 东北林业大学,黑龙江,哈尔滨,150040
2. 吉林省交通规费征收管理局吉林分局,吉林,吉林,132000
3. 哈尔滨理工大学,黑龙江,哈尔滨,150040
摘    要:介绍了BP网络在手写体数字识别中的应用,并在神经网络中引入部分连接结构。实验证明,在神经网络中引入部分连接功能可以大大增强网络的灵活性,可以根据不同的应用来调节网络密度,以达到网络的最高性能。目前识别率为94.61%,实验结果表明,BP神经网络可成功地用于手写数字字符的识别问题。

关 键 词:手写体数字识别  BP网络  应用  BP神经网络  连接结构  实验证明  连接功能  网络密度  识别问题  数字字符  灵活性  识别率
文章编号:1006-5091(2005)02-0038-05

The Application of BP neural Network in Handwritten Digit Recognition
ZHAO Wei,WANG Jun-hong,LI Juan,LU Zhao-tang.The Application of BP neural Network in Handwritten Digit Recognition[J].Forestry Labour Safety,2005,18(2):38-42,44.
Authors:ZHAO Wei  WANG Jun-hong  LI Juan  LU Zhao-tang
Abstract:The application of BP neural network in the handwritten digit recognition and the use of partial link structure in the neural network are introduced. The experiment has proved that the introduction of the partial link function in the neural network can strengthen the flexibility of the network greatly and network density can be adjusted according to different applications to achieve the best performance of the network. Now the system can achieve a recognition ratio of 94. 61%. The experimental result shows that the BP neural network can be used for handwritten alphanumeric character recognition successfully.
Keywords:digit recognition  BP neural network  partial link  application  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号