首页 | 本学科首页   官方微博 | 高级检索  
     

基于ART1网络的字符识别器
引用本文:杨戈,莫青青,黄静.基于ART1网络的字符识别器[J].计算机系统应用,2014,23(12):136-141.
作者姓名:杨戈  莫青青  黄静
作者单位:1. 北京师范大学珠海分校信息技术学院,珠海 519087; 北京大学深圳研究生院深圳物联网智能感知技术工程实验室,深圳 518055
2. 北京师范大学珠海分校信息技术学院,珠海,519087
基金项目:国家自然科学基金(61272364);广东省学科建设专项资金(2013WYXM0122);深圳市科技计划项目及基础研究计划(JC201005270275A);深圳市战略性新兴产业发展专项资金 (JCYJ20120614144655154);北京师范大学珠海分校科研创新团队(201251006);北京师范大学珠海分校教改项目(201329)
摘    要:通过标准自适应共振理论神经网络(Adaptive Resonance Theory, ART),设计和实现了一个字符识别器,针对标准的 ART1网络存在的不足,即网络的学习不稳定,对样本输入顺序比较敏感等问题,给出了改进方法,用C语言实现了这2种字符识别器,实验结果表明这2种字符识别器能够对不同的字符进行识别,改进方法比基于标准ART1网络具有更好的稳定性。

关 键 词:人工神经元网络  自适应共振理论  ART1  C语言
收稿时间:2014/3/24 0:00:00
修稿时间:2014/7/11 0:00:00

Character Recognizer Based on ART1 Network
YANG Ge,MO Qing-Qing and HUANG Jing.Character Recognizer Based on ART1 Network[J].Computer Systems& Applications,2014,23(12):136-141.
Authors:YANG Ge  MO Qing-Qing and HUANG Jing
Affiliation:College of Information Technology, Beijing Normal University Zhuhai Campus, Zhuhai 519087, China;Engineering Lab on Intelligent Perception for Internet of Things ELIP, Shenzhen Graduate School, Peking University, Shenzhen 518055, China;College of Information Technology, Beijing Normal University Zhuhai Campus, Zhuhai 519087, China;College of Information Technology, Beijing Normal University Zhuhai Campus, Zhuhai 519087, China
Abstract:Adaptive Resonance Theory (ART) neural network is analyzed in this paper. A character recognizer is designed and implemented based on the standard ART1 network, aiming at the shortcomings of the standard ART1 network, which concludes the unstablity of network learning and the over sensitiveness to the input sample sequence. This paper gives a method to improve the implementation in C 2 kind of identifier. Experimental validation of these two character recognizer can identify the different character. The improvement method based on standard ART1 network has better stability.
Keywords:artificial neural network  adaptive resonance theory  ART1  C language
本文献已被 万方数据 等数据库收录!
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载全文
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