| 基于退化HMM的印刷体文字识别研究 |
| |
| 引用本文： | 金长龙 吴迪. 基于退化HMM的印刷体文字识别研究[J]. 延边大学学报(自然科学版), 2005, 31(4): 290-293 |
| |
| 作者姓名： | 金长龙 吴迪 |
| |
| 作者单位： | 延边大学工学院计算机科学与技术系,吉林延吉133002 |
| |
| 摘 要： | 提出一种新的基于退化隐马尔柯夫模型的印刷体文字识别方法.此方法按照一定规则提取文字的一维笔段序列特征,然后将该特征输入到设计好的分类器中进行分类.在分类器的设计上摒弃传统的左右型结构模型,采用了遍历型结构模型.实验证明此方法能够更好地完成文字分类任务,识别率可以达到99%以上.
|
| 关 键 词： | 退化HMM 文字识别 细化 |
| 文章编号： | 1004-4353(2005)04-0290-04 |
| 收稿时间： | 2005-05-13 |
| 修稿时间： | 2005-05-13 |
Study on printed Chinese character recognition based on DHMM |
| |
| JIN Chang-long, WU Di. Study on printed Chinese character recognition based on DHMM[J]. Journal of Yanbian University (Natural Science), 2005, 31(4): 290-293 |
| |
| Authors: | JIN Chang-long WU Di |
| |
| Affiliation: | JIN Chang-long, WU Di Department of Computer Science and Technology, College of Engineering, Yanbian University, Yanji 133002, China ) |
| |
| Abstract: | A novel printed character recognition method based on degraded Hidden Markov Model(DHMM) is(proposed,) which can be applied to engineering.We extract 1D stroke sequence as the feature of the(character) under some rules and then put it into the classifier we designed.For the design of classifier,we adopt the(ergodic) model instead of the traditional left-right model.Experimental results showed the recognition rate of classifier with ergodic model is 99%. |
| |
| Keywords: | degraded Hidden Markov Model optical character recognition thinning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
