| 大量目标识别的光学相关与神经网络融合方法 |
| |
| 引用本文： | 张延炘,刘玥,陈天仑.大量目标识别的光学相关与神经网络融合方法[J].四川激光,2000,21(3):44-46. |
| |
| 作者姓名： | 张延炘 刘玥 陈天仑 |
| |
| 作者单位： | 南开大学现代光学研究所物理系!天津300071(张延炘，刘玥)，光电信息技术科学教育部重点实验室!天津300071(陈天仑) |
| |
| 基金项目： | 国家自然科学基金资助的课题!(No.6 98770 0 5) |
| |
| 摘 要： | 本文基于光学相关与神经网络学习算法和编码聚类原理的融合 ,提出一种大数量目标的高效率分类识别方法 ,并以 67个字符 ,其中包括2 6个英文字母、1 0个数字和 31个省和直辖市的简称汉字的分类识别作为实例 ,给出详细的原理说明和结果。
|
| 关 键 词： | 神经网络 光学相关模式识别 聚类编码 |
Fusion of OCPR and neural network for recognition of large number targets |
| |
| Zhang Yanxin,Liu Yue,Chen Tianlun.Fusion of OCPR and neural network for recognition of large number targets[J].Laser Journal,2000,21(3):44-46. |
| |
| Authors: | Zhang Yanxin Liu Yue Chen Tianlun |
| |
| Abstract: | An effective method of recognition of targets with large number is proposed based on fusion of optical correlation pattern recognition(OCPR) and neural network learning algorithm and clustering encoding.Detailed principle and recognition results on 67 characters,including 26 English capitals,10 digits and 31 Chinese characters which are the abbreviations of provinces and municipalities,as a case study,are presented in this paper. |
| |
| Keywords: | neural network optical correlation pattern recognition(OCPR) learning algorithm clustering encoding |
| 本文献已被 CNKI 维普 等数据库收录！ |
