| 印刷体英文文档识别系统的设计与实现 |
| |
| 引用本文： | 尹芳,王卫兵,陈德运. 印刷体英文文档识别系统的设计与实现[J]. 哈尔滨理工大学学报, 2008, 13(6) |
| |
| 作者姓名： | 尹芳 王卫兵 陈德运 |
| |
| 作者单位： | 哈尔滨理工大学,计算机科学与技术学院,黑龙江,哈尔滨,150080 |
| |
| 基金项目： | 哈尔滨理工大学青年基金 |
| |
| 摘 要： | 光学字符识别是模式识别领域的一个重要分支.提出并实现了一种用于印刷体英文文档的OCR系统.该系统使用基于字符识别的方法进行文档识别,图像经过预处理后,提取多种特征进行组合,并且考虑到字符粘连的情况,在训练样本中加入部分易粘连字母组合进行识别.通过实验证明,该识别系统快速、稳定且有效.
|
| 关 键 词： | 英文文档识别 特征提取 特征组合 |
Architecture and Implementation of the Printed English Documentation Recognition System |
| |
| YIN Fang,WANG Wei-bing,CHEN De-yun. Architecture and Implementation of the Printed English Documentation Recognition System[J]. Journal of Harbin University of Science and Technology, 2008, 13(6) |
| |
| Authors: | YIN Fang WANG Wei-bing CHEN De-yun |
| |
| Affiliation: | YIN Fang,WANG Wei-bing,CHEN De-yun(School of Computer Science , Technology,Harbin University of Science , Technology,Harbin 150080,China) |
| |
| Abstract: | Optical character recognition(OCR) is an important branch of pattern recognition.This paper puts forward and achieves an OCR system to recognize printed English documentation.It uses a method to identify documents based on the use of character recognition method.After preprocess,a variety of features is extracted to combine and recognize.Considering character sticking,some multi-character training samples are added into the training sample set.Experiment result shows that the system is fast,stable and effec... |
| |
| Keywords: | English documentation recognition feature extraction feature combination |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
