| 基于数学形态谱和二维矢量分类网络的模式识别及二维矢量分类网络的光学实现 |
| |
| 引用本文： | 王宁,刘立人,梁丰.基于数学形态谱和二维矢量分类网络的模式识别及二维矢量分类网络的光学实现[J].光学学报,1996,16(6):763-767. |
| |
| 作者姓名： | 王宁 刘立人 梁丰 |
| |
| 作者单位： | 中国科学院上海光学精密机械研究所!上海，201800，中国科学院上海光学精密机械研究所!上海，201800，中国科学院上海光学精密机械研究所!上海，201800 |
| |
| 基金项目： | 国家基金委，高技术局资助 |
| |
| 摘 要： | 介绍一种基于数学形态谱和二维矢量分类网络的模式识别体系。数学形态谱相对于图像平移和旋转不变。建立了光学二维矢量分类网络，利用光学逻辑操作和最大值网络的循环操作，得到与输入图像最佳匹配的模式。
|
| 关 键 词： | 归一数学形态谱 二维矢量分类网络及光学实现 |
| 收稿时间： | 1995/5/19 |
Shift, Rotation Invariant Pattern Recognition Based on Morphology Pattern Spectrum and 2-D Vector Quantization Network and the Optical Implementation of 2-D Vector Quantization Network |
| |
| Wang Ning,Liu Liren,Liang Feng.Shift, Rotation Invariant Pattern Recognition Based on Morphology Pattern Spectrum and 2-D Vector Quantization Network and the Optical Implementation of 2-D Vector Quantization Network[J].Acta Optica Sinica,1996,16(6):763-767. |
| |
| Authors: | Wang Ning Liu Liren Liang Feng |
| |
| Abstract: | In this paper, we propose a shift and rotation invariant pattern recognition architecture, using morphology pattern spectrum as image feature representation and 2-D vector quantization network as vector classifier. Morphology pattern spectrum is invariant not to image shift, but to image rotation when the structure element is rotationally symmetric. We use it constructing a feature vector of an image to train a 2-D vector quantization network. After training, it can implement the classification of feature vector. The optical implementation of the 2-D vector quantization network is dementrated and the experiment results are given. |
| |
| Keywords: | pattern recognition 2-D vector quantization network morphology pattern spectrum optical implementation |
| 本文献已被 CNKI 等数据库收录！ |
