| 基于支持向量机的手写体数字识别 |
| |
| 引用本文： | 尚磊,刘风进.基于支持向量机的手写体数字识别[J].兵工自动化,2007,26(3):39-41. |
| |
| 作者姓名： | 尚磊 刘风进 |
| |
| 作者单位： | 防空兵指挥学院,研究生17队,河南,郑州,450052;新疆军区高炮旅,司令部,新疆,乌鲁木齐,830017 |
| |
| 摘 要： | 支持向量机的手写体数字识别中,采用美国邮政服务数据库.并取多个2层神经网络中的最好者得出2层神经网络结果,专门设计5层卷积神经网络Lenetl.所有的结果均直接采用点阵输入,将像素值归正到相应区域间,且不施加任何预处理.该方法与人工分类、神经网络、决策树等方法比较,其测试误差低,测试速度高.
|
| 关 键 词： | 支持向量机 手写体数字识别 卷积神经网络 |
| 文章编号： | 1006-1576（2007）03-0039-03 |
| 收稿时间： | 2006-08-22 |
| 修稿时间： | 2007-01-16 |
Handwritten Number Recognition Based on Support Vector Machine |
| |
| SHANG Lei,LIU Feng-jin.Handwritten Number Recognition Based on Support Vector Machine[J].Ordnance Industry Automation,2007,26(3):39-41. |
| |
| Authors: | SHANG Lei LIU Feng-jin |
| |
| Affiliation: | 1. No. 17 Brigade of Graduate, Air Defense Forces Command Academy, Zbengzhou 450052, China; 2. Command headquarter, Air Defense Artillery Brigade of Xinjiang Provincial Military Region, Ummchi 830017, China |
| |
| Abstract: | Handwritten number recognition based on support vector machine adopts the US post service database. Moreover,it calculate the two-layer nerve network results based on several best two-layer nerve networks and design five-layer convolution nerve networks Lenetl. All results are inputted by using lattice input. The image point value is sent to the corresponding area without pretreatment. Compared with artificial classification,nerve network,and decision tree,its test error is low and the speed is high. |
| |
| Keywords: | SVM(Support Vector Machine) Handwritten number recognition Convolution nerve network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
