| 一种基于投影变换和神经网络的字符识别方法 |
| |
| 引用本文： | 李保平,韩润萍.一种基于投影变换和神经网络的字符识别方法[J].北京服装学院学报,2008,28(1):55-59. |
| |
| 作者姓名： | 李保平 韩润萍 |
| |
| 作者单位： | 北京服装学院工业设计与信息工程学院,北京,100029;北京服装学院工业设计与信息工程学院,北京,100029 |
| |
| 摘 要： | 提出了一种基于投影变换和BP神经网络的字符识别方法,该方法集成了投影变换和神经网络的优势,可有效地提高机动车牌照上的字符的识别率、识别速度以及识别系统的泛化能力.用MATLAB构建字符识别网络进行仿真测试,结果表明该方法是有效的,测试识别率可达96%.
|
| 关 键 词： | 投影变换 BP神经网络 字符识别 仿真 |
| 文章编号： | 1001-0564（2008）01-0055-05 |
| 收稿时间： | 2007-09-19 |
A Character Recognition Method Based on Projection Transform and Neural Network |
| |
| LI Bao-ping,HAN Run-ping.A Character Recognition Method Based on Projection Transform and Neural Network[J].Journal of Beijing Institute of Clothing Technology(Nature Science Edition),2008,28(1):55-59. |
| |
| Authors: | LI Bao-ping HAN Run-ping |
| |
| Abstract: | Presented a method of character recognition based on projection transform and BPNN, which combined the advantages of projection transform and BPNN. The method could not only improve the recognition rate and speed of the letter and number On the license plate, but also improve the generalization ability of the recognition system. The simulation test results showed that the method was effective and the recognition rate could attain to 96 percent. |
| |
| Keywords: | projection transform BP neural network character recognition simulation |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
