| 一种有效的多字体印刷字符识别系统实现 |
| |
| 引用本文： | 赵全友,潘保昌,姚锦秀,郑胜林,陈箫枫.一种有效的多字体印刷字符识别系统实现[J].重庆邮电学院学报(自然科学版),2005,17(4):451-455. |
| |
| 作者姓名： | 赵全友 潘保昌 姚锦秀 郑胜林 陈箫枫 |
| |
| 作者单位： | 广东工业大学信息工程学院 广东广州510640
(赵全友，潘保昌，姚锦秀，郑胜林)，广东工业大学信息工程学院 广东广州510640(陈箫枫) |
| |
| 摘 要： | 提出了一种基于神经网络和浮动模板的多字体印刷字符识别方法。在研究大量的多字体印刷字符图像后，给出了一种有效的预处理方法，并在综合抽取宏观特征与微观特征后，送入神经网络的浮动模板法分类器进行识别。实验证明该方法具有相当高的识别率，应用前景十分广泛。
|
| 关 键 词： | 多字体识别 预处理 特征提取 神经网络：浮动模板法 |
Implementation of effective multifont printed character recognition system |
| |
| ZHAO Quan-you,PAN Bao-chang,YAO Jin-xiu,ZHENG Sheng-lin,CHEN xiao-feng.Implementation of effective multifont printed character recognition system[J].Journal of Chongqing University of Posts and Telecommunications(Natural Sciences Edition),2005,17(4):451-455. |
| |
| Authors: | ZHAO Quan-you PAN Bao-chang YAO Jin-xiu ZHENG Sheng-lin CHEN xiao-feng |
| |
| Abstract: | A multifont printed character recognition based on floating mask method and neural network is presented in this paper. After researching on many multifont printed character images, authors give an effective preprocessing method. Then the macro features and the micro features are extracted, which are to be sent to the BP neural network. The classifier of combination of the neural network and the floating mask yields the right results of classification.The experiment proves this method can get very high recognition rate.The prospect of its application in many fields is obvious. |
| |
| Keywords: | multifont character recognition preprocessing feature extracting neural network floating mask method |
| 本文献已被 CNKI 维普 等数据库收录！ |
