| 用于手写体汉字识别的汉字结构模型 |
| |
| 引用本文： | 刘峡壁,贾云得. 用于手写体汉字识别的汉字结构模型[J]. 北京理工大学学报, 2003, 23(3): 322-326 |
| |
| 作者姓名： | 刘峡壁 贾云得 |
| |
| 作者单位： | 北京理工大学,信息科学技术学院计算机科学工程系,北京,100081 |
| |
| 摘 要： | 针对手写体汉字识别问题，选取笔段和笔划作为基元，分析手写体汉字的组成规律和变形规律，提出了两种汉字结构模型：笔段中心点模型和笔划关系矩阵模型，以及基于模型的分类依据和识别方法．根据所提出的模型，采用两级分类方案构造汉字识别系统，粗分类采用笔段中心点法，细分类采用笔划关系矩阵法．实验表明模型是有效可行的．
|
| 关 键 词： | 手写体汉字识别 结构模型 笔段中心点 笔划关系矩阵 |
| 文章编号： | 1001-0645(2003)03-0322-05 |
| 收稿时间： | 2002-09-09 |
| 修稿时间： | 2002-09-09 |
Chinese Character Structure Models for Handwritten Chinese Character Recognition |
| |
| LIU Xia bi and JIA Yun de. Chinese Character Structure Models for Handwritten Chinese Character Recognition[J]. Journal of Beijing Institute of Technology(Natural Science Edition), 2003, 23(3): 322-326 |
| |
| Authors: | LIU Xia bi and JIA Yun de |
| |
| Affiliation: | Department of Computer Science and Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing100081, China;Department of Computer Science and Engineering, School of Information Science and Technology, Beijing Institute of Technology, Beijing100081, China |
| |
| Abstract: | By choosing stroke and sub stroke as basic components to analyse the composition regularities and deformation regularities of handwritten Chinese character, two models are presented for representing the structure for handwritten Chinese character recognition: the sub stroke center model and the stroke relation matrix model, as the classifying criteria and methods based on models. According to the proposed models, a two stage Chinese character recognition system is developed, that applies the sub stroke center model in the first stage and stroke relation matrix model in the second stage. Experimental results show the feasibility and effectiveness of the proposed models. |
| |
| Keywords: | handwritten Chinese character recognition structural model sub-stroke center stroke relation matrix |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京理工大学学报》浏览原始摘要信息 |
|
点击此处可从《北京理工大学学报》下载全文 |
