| 基于神经网络集成的手写识别系统 |
| |
| 引用本文： | 马婉婕,孙虎元,孙立娟,孙晓光.基于神经网络集成的手写识别系统[J].计算机应用与软件,2009,26(8):5-7,44. |
| |
| 作者姓名： | 马婉婕 孙虎元 孙立娟 孙晓光 |
| |
| 作者单位： | 1. 复旦大学计算机与信息技术系,上海,200433
2. 中国科学院海洋研究所,山东,青岛,266071 |
| |
| 基金项目： | 国家自然科学基金项目，上海市自然科学基金 |
| |
| 摘 要： | 在研究基于隐马尔可夫模型的识别器和基于距离分类器的识别器的识别结果基础上,提出两种基于集成神经网络的手写识别系统:比较神经网络识别系统和全排列神经网络识别系统.实验分析表明,该系统对西文手写体的识别率最高可达到99%,比单独使用原始识别器的识别率提高10个百分点,达到了良好的识别效果.
|
| 关 键 词： | 手写识别 神经网络 隐马尔可夫模型 距离分类器 |
HANDWRITING RECOGNITION SYSTEM BASED ON NEURAL NETWORK ENSEMBLE |
| |
| Ma Wanjie,Sun Huyuan,Sun Lijuan,Sun Xiaoguang.HANDWRITING RECOGNITION SYSTEM BASED ON NEURAL NETWORK ENSEMBLE[J].Computer Applications and Software,2009,26(8):5-7,44. |
| |
| Authors: | Ma Wanjie Sun Huyuan Sun Lijuan Sun Xiaoguang |
| |
| Affiliation: | Department of Computing and Information Technology;Fudan University;Shanghai 200433;China;Institute of Oceanology;Chinese Academy of Sciences;Qingdao 266071;Shangdong;China |
| |
| Abstract: | According to the study result of the recognizers based on Hidden Markova Model and on distance classification respectively,in this paper we introduce two handwriting recognition systems based on neural network ensemble,the comparison neural network recognition system and the permutation neural network recognition system.Experimental analyses express that the recognition accuracy of the system on handwriting of western languages could be up to 99%,i.e.10 percentage points higher than just using the primary r... |
| |
| Keywords: | Handwriting recognition Neural network Hidden Markov model Distance classifier |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
