| 一种用于多目标旋转不变分类识别的神经网络模型及算法 |
| |
| 引用本文： | 常胜江,申金媛.一种用于多目标旋转不变分类识别的神经网络模型及算法[J].光学学报,1998,18(12):663-1668. |
| |
| 作者姓名： | 常胜江 申金媛 |
| |
| 作者单位： | 南开大学现代光学研究所国家教委光学信息科学技术开放实验室 |
| |
| 基金项目： | 国家自然科学基金,南开大学自然科学基金 |
| |
| 摘 要： | 提出了一种适于光学实现的神经网络模型和算法，通过对３种飞行器平面内旋转投影较的识别，证明了该方法具有对多目标转动不变的模式识别能力。
|
| 关 键 词： | 目标旋转 分类识别 神经网络模型 算法 |
| 收稿时间： | 1997/6/6 |
A Cascaded Model of Neural Networks and Its Learning Algorithm for Pattern Recognition with Rotation Invariance |
| |
| Chang Shengjiang,Shen Jinyuan,Liu Yue,Song Zhuang Zhai Hongchen,Zhang Yanxin.A Cascaded Model of Neural Networks and Its Learning Algorithm for Pattern Recognition with Rotation Invariance[J].Acta Optica Sinica,1998,18(12):663-1668. |
| |
| Authors: | Chang Shengjiang Shen Jinyuan Liu Yue Song Zhuang Zhai Hongchen Zhang Yanxin |
| |
| Abstract: | A model of neural networks and its learning algorithm suitable for optical implementation are proposed. As an example, the model is applied to recognize the projective image of three kinds of aircraft. Computer simulations and optical experiment have shown that this model can be successfully used to error tolerance pattern recognition of multiple targets with arbitrary orientations. |
| |
| Keywords: | interconnection weights gray level adaptive clipping |
| 本文献已被 CNKI 维普 等数据库收录！ |
