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。
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.
出处
《光学学报》
EI
CAS
CSCD
北大核心
1996年第6期763-767,共5页
Acta Optica Sinica
基金
国家基金委
高技术局资助
关键词
二维矢量
分类网络
光学实现
pattern recognition
2-D vector quantization network
morphology pattern spectrum
optical implementation