| 基于组合特征的多分类器集成的脱机手写体彝文字识别 |
| |
| 引用本文： | 朱龙华,王嘉梅. 基于组合特征的多分类器集成的脱机手写体彝文字识别[J]. 云南民族大学学报(自然科学版), 2010, 19(5). DOI: 10.3969/j.issn.1672-8513.2010.05.005 |
| |
| 作者姓名： | 朱龙华 王嘉梅 |
| |
| 作者单位： | 云南民族大学,电气信息工程学院,云南,昆明,650031 |
| |
| 基金项目： | 国家民委科学研究基金，云南民族大学"彝文古籍数字化研究"基地资助项目 |
| |
| 摘 要： | 组合特征的多分类器集成是提高脱机手写体字符识别率的一种发展趋势,选用2组具有统计特征的组合特征对脱机手写体彝文字进行识别:第1组,使用应用广泛的弹性网格特征、笔划密度特征;第2组,使用方向线素特征和投影特征;同时本文提出一种基于笔划粗切割的特征提取方法用于彝文字的结构特征的提取.最后通过多分类器集成方案输出识别结果.实验结果表明,该方法能得到比较理想的识别效果.
|
| 关 键 词： | 组合特征 脱机手写体 多分类器集成 彝文字识别 笔划粗切割 |
Off-Line Handwritten Yi Character Recognition Based on the Multi-Classifier Ensemble with Combination Features |
| |
| ZHU Long-hua,WANG Jia-mei. Off-Line Handwritten Yi Character Recognition Based on the Multi-Classifier Ensemble with Combination Features[J]. Journal of Yunnan Nationalities University:Natural Sciences Edition, 2010, 19(5). DOI: 10.3969/j.issn.1672-8513.2010.05.005 |
| |
| Authors: | ZHU Long-hua WANG Jia-mei |
| |
| Affiliation: | ZHU Long-hua,WANG Jia-mei(School of Electrical and Information Technology,Yunnan University of Nationalities,Kunming 650031,China) |
| |
| Abstract: | The multi-classifier ensemble with combination features is a means to improve the off-Line handwritten character recognition rate.This research uses two groups which have statistical characteristics of combination features for the recognition of offline handwritten Yi characters.The first group adopts the extensive application of the elastic mesh features and stroke density features;the second group adopts the directional line element feature and projection feature.The research presents a new feature extrac... |
| |
| Keywords: | combination features off-Line handwritten multi-classifier ensemble recognition of Yi characters rough-cutting stroke |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
