| 基于小波变换和ART网络的手写数字识别 |
| |
| 引用本文： | 张捷,黄光球,封俊红. 基于小波变换和ART网络的手写数字识别[J]. 微型电脑应用, 2006, 22(12): 38-40 |
| |
| 作者姓名： | 张捷 黄光球 封俊红 |
| |
| 作者单位： | 西安建筑科技大学管理学院,西安,710055 |
| |
| 基金项目： | 陕西省教育厅专项基金资助项目(01JK201) |
| |
| 摘 要： | 由于小波变换能有效地提取字符的结构特征,自适应共振(ART)网络有很好的学习能力。本文将二者结合起来,用小波变换抽取特征、用自适应共振ART网络作模式分类器来识别手写数字。实验证明该方法有很高的识别率,能够有效地进行手写数字的分类,可以满足实际应用。
|
| 关 键 词： | 手写数字识别 小波变换 ART网络 |
| 文章编号： | 1007-757X（2006）12-0038-03 |
| 收稿时间： | 2006-06-22 |
| 修稿时间： | 2006-06-22 |
Handwritten Digital Recognition Based on Wavelet Transform and ART Neural Networks |
| |
| ZHANG Jie,HUANG Guang-qiu,FENG Jun-hong. Handwritten Digital Recognition Based on Wavelet Transform and ART Neural Networks[J]. Microcomputer Applications, 2006, 22(12): 38-40 |
| |
| Authors: | ZHANG Jie HUANG Guang-qiu FENG Jun-hong |
| |
| Abstract: | Because that wavelet transform can effectively extract the characters, the Adaptive Resonance Theory (ART) Neural Networks has a good learning ability. This paper combines the two aspects to recognize handwritten digits by using wavelet transform to extract feature and Adaptive Resonance Theory (ART) Neural Networks for Classification. The result of experiment shows high recognition rate, which indicates that the method can effectively classify handwritten digits and be put into practical use. |
| |
| Keywords: | Handwritten digital recognition Wavelet transform ART neural networks |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
