| 一种基于Hough变换的神经网络字符识别方法 |
| |
| 引用本文： | 郑胜林,彭明明,潘保昌.一种基于Hough变换的神经网络字符识别方法[J].广东工业大学学报,2003,20(4):73-77. |
| |
| 作者姓名： | 郑胜林 彭明明 潘保昌 |
| |
| 作者单位： | 1. 广东工业大学,信息工程学院,广东,广州,510643
2. 华南农业大学,信息学院计算机系,广东,广州,510642 |
| |
| 基金项目： | 2000年广东省教育厅自然科学研究项目(Z02031) |
| |
| 摘 要： | 针对印刷体字符的结构特点，利用Hough变换的点一线对偶性，提出了一种新的印刷体字符识别方法。该方法将字符在参数空间中共线点的个数及其坐标，作为BP神经网络识别系统的特征输入矢量，获得了较好的识别效果。
|
| 关 键 词： | Hough变换 BP神经网络 印刷体字符识别 参数空间中共线点 模式识别 |
| 文章编号： | 1007-7162(2003)04-0073-05 |
| 修稿时间： | 2002年10月29 |
A Method for Characters Recognition Based on the Hough Transform and Neural Network |
| |
| ZHENG Shen-lin,PENG Ming-ming,PAN Bao-chang.A Method for Characters Recognition Based on the Hough Transform and Neural Network[J].Journal of Guangdong University of Technology,2003,20(4):73-77. |
| |
| Authors: | ZHENG Shen-lin PENG Ming-ming PAN Bao-chang |
| |
| Abstract: | This paper presents a new method for printed characters recognition according to the property of printed characters' structure hy using the duality of point-line in Hough transform. In this method, the number of the points which are on the same line and its corresponding coordinate in a character's parametric space are used as the feature input vector of BP neural network recognition system and a better result has been gotten. |
| |
| Keywords: | Hough transform BP neural network printed characters recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
