| 基于神经网络的字符识别技术研究 |
| |
| 引用本文： | 黄瀚敏 易正俊. 基于神经网络的字符识别技术研究[J]. 重庆大学学报(自然科学版), 1999, 22(6): 59-65 |
| |
| 作者姓名： | 黄瀚敏 易正俊 |
| |
| 作者单位： | 重庆大学自动化学院!重庆400044 |
| |
| 摘 要： | 本文在分析人工神经网络理论和图象处理及其特征提取理论的基础上，探讨了网络结构、特征编码、算法的实现、学习样本的收集、网络参数的选择及ＢＰ算法缺陷等问题，设计并实现了一种基于神经网络的字符识别系统。
|
| 关 键 词： | 人工神经网络 图象处理 BP算法 手写字符识别 |
Study on ANN Based Character Recognition |
| |
| HUANG Han min,YI Zheng jun,WANG Xian ju,WANG Rui fang. Study on ANN Based Character Recognition[J]. Journal of Chongqing University(Natural Science Edition), 1999, 22(6): 59-65 |
| |
| Authors: | HUANG Han min YI Zheng jun WANG Xian ju WANG Rui fang |
| |
| Abstract: | The theory of Artificial Neural Networks and image processing are analyzed. ANN theory is also investigated . A Back Propagation network is used for classification. Based on the ANN and feature extraction, a character recognition and entry system is developed. Its drawbacks are discussed. Some solutions are presented. An odd feature database is constructed to promote the performance for learning. A 3 layer feedforward network has been proved that it has the ability to identify hand written characters. |
| |
| Keywords: | ANN image processing Back Propagation network hand written characters recognition |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《重庆大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《重庆大学学报(自然科学版)》下载免费的PDF全文 |
