本文已被:浏览 1462次 下载 2745次
Received:April 03, 2013 Revised:July 02, 2013
Received:April 03, 2013 Revised:July 02, 2013
中文摘要: 本文简单介绍了人工神经元网络的背景知识, 提出了一种利用传统BP(Back-Propagation 误差逆传播)网络识别印刷字符的方法, 用C语言对其进行了实现. 在进行了大量实验之后, 实验结果表明该字符识别器具有较好的有效性和正确性, 能够在合理的误差范围内以较好的效率成功识别字符.
Abstract:This paper introduced the background knowledge of Artificial Neural Network and a way to use BP network to recognize printed characters was proposed, which was implemented with C language. After a lot of experiments, the experimental results show that the character recognizer has good validity and correctness. Besides, the printed characters can be recognized successful within the reasonable range of error.
文章编号: 中图分类号: 文献标志码:
基金项目:国家自然科学基金(60875050,61272364);国家高技术研究发展计划(863计划)(2006AA04Z247);广东省自然科学基金(9151806001000025);
深圳市科技计划项目及基础研究计划项目(JC201005270275A);深圳市战略性新兴产业发展专项资金项目(JCYJ20120614144655154);
北京师范大学珠海分校科研创新团队(多媒体传输与计算机视觉研究团队,201251006);北京师范大学珠海分校教改项目(201329)
引用文本:
杨戈,谢思路.一个基于BP网络的字符识别器.计算机系统应用,2013,22(10):163-168
YANG Ge,XIE Si-Lu.Character Recognizer Based on BP Network.COMPUTER SYSTEMS APPLICATIONS,2013,22(10):163-168
杨戈,谢思路.一个基于BP网络的字符识别器.计算机系统应用,2013,22(10):163-168
YANG Ge,XIE Si-Lu.Character Recognizer Based on BP Network.COMPUTER SYSTEMS APPLICATIONS,2013,22(10):163-168