9299.net
大学生考试网 让学习变简单
当前位置:首页 >> 军事 >>

基于bp神经网络的字母识别系统设计与实现_本科论文

基于bp神经网络的字母识别系统设计与实现_本科论文

济南大学泉城学院 毕 题 目 业 论 文 基于 BP 神经网络的字母识别系统 设计与实现 专 班 学 学 业 级 生 号 电气工程及其自动化 07Q2 指导教师 二〇一一年六月七日 济南大学泉城学院毕业论文 摘 要 基于前向反馈神经网络的字母识别技术在科学技术日新月异的今天迅速得 到发展,在诸多的方面得到应用包括出版、金融、军事、现金登记、页面浏览以 及任何带有重复性、变化性数据的文件。 英文字母识别系统的设计经过以下几个过程:预处理、特征提取、BP 神经 网络的训练、识别。本文的重点在于 BP 神经网络。 本文运用的是三层神经网络,输入层、隐含层、输出层。隐含层节点的确定 本文给出了多种方法,本文运用了根值的方法。 基于人工神经网络字母识别的特点和优越性,主要表现在三个方面: 第一,具有自学习功能。字母识别时,只在先把许多不同的图像样板和对应 的应识别的结果输入人工神经网络,然后在识别之前对神经网络进行训练形成稳 定的权值这样网络通过自学习功能,慢慢学会识别类似的图像。第二,具有联想 存储功能。用人工神经网络的反馈网络在字母识别时可以实现这种联想。第三, 具有高速寻找优化解的能力。字母识别时寻找一个复杂问题的优化解,往往需要 很大的计算量 , 利用一个针对某问题而设计的反馈型人工神经网络的字母识别系 统,发挥计算机的高速运算能力,可能很快找到优化解。 本文是在 matlab 环境下模拟整个英文字母的识别过程,随着科学技术的发 展识别技术更加成熟,各种难题都将会得到解决。 关键词:字母识别;图像处理;特征提取;BP 神经网络 -I- 济南大学泉城学院毕业论文 ABSTRACT Today the science and technology develop rapidly. Letter recognition technology based on the feedback neural network is applied in many aspects including publication, finance military, cash register, page views, and any with repeatability,and variability of data files . Letter Identification System include the following processes: preprocessing, feature extraction, BP neural network training,and recognition.. In this paper, we use a three-layer neural network, including input layer, hidden layer and output layer. This paper supply of a variety of methods to determine Hidden layer nodes . The root sign method and other method.that proposed by the Nelson and Illingwnrth are applied . The features and advantages of Artificial neural network is reflected in three aspects : First, a self-learning function. When we recognize letters, only putting many different images and the corresponding results into the artificial neural network and forming a stable weight before the letter recognition,the network will be through self-learning function to slowly identify similar images.Second, with the association storage. Artificial neural network feedback network can achieve this association in the letter recognition. Third, finding the optimal solution with high capacity. Finding the optimal solution of a complex often require a large amount of computation.Using a design that a feedback type artificial neural network for problem and playing the high-speed computing power of computer, you may quickly find the optimal solution. In the matlab environment this article simulate the entire process of letter recognition, with the development of science and technology recognition technology is more mature and have various problems will be solved. Keywords:Letter identificati

网站首页 | 网站地图 | 学霸百科 | 新词新语
All rights reserved Powered by 大学生考试网 9299.net
文档资料库内容来自网络,如有侵犯请联系客服。zhit325@qq.com