您的位置:首页  > 论文页面

基于Hopfield网络的英文字母识别

发表时间:2009-01-15  浏览量:3305  下载量:867
全部作者: 韩基超,刘武寅,李茜,郭嗣琮
作者单位: 辽宁工程技术大学理学院
摘 要: 应用Hopfield神经网络作为联想存储器解决英文字母图像识别问题,将每个字母看作一个图像并从中提取出原始数据,把原始数据提取部分作为网络学习的数据,计算出正确的权值,建立起网络模型,再将要识别的字母图像代入网络,对字母图像进行识别。分析了Hopfield神经网络如何识别大写英文字母,展示了Hopfield神经网络在模式识别中的有效性和实用性,以及Hopfield神经网络的容错能力,并给出了模式识别过程中Matlab软件的实现方法。
关 键 词: 应用数学;Hopfield网络;联想存储器;模式识别
Title: The recognition for English letters using Hopfield network
Author: HAN Jichao, LIU Wuyin, LI Qian, GUO Sicong
Organization: College of Science, Liaoning Technical University
Abstract: This article uses Hopfield network as content addressed storage to conduct pattern recognition of English letters image. Every letter is considered as an image and raw date is extracted from it, the extracted raw data is taken as the data of network studying, the correct weight is calculated and a network model is established. Then the English letter image which needs to be recognized is substituted into the network and the recognition is carried out. This article analyzes how the Hopfield network is used to identify the capital English letters, demonstrates the effectiveness and practicality of Hopfield network in the pattern recognition and its fault-tolerant ability, and also gives the realization of Matlab software in process of pattern recognition.
Key words: applied mathematics; Hopfield network; content addressed storage; pattern recognition
发表期数: 2009年1月第1期
引用格式: 韩基超,刘武寅,李茜,等. 基于Hopfield网络的英文字母识别[J]. 中国科技论文在线精品论文,2009,2(1):33-39.
 
4 评论数 0
暂无评论
友情链接