摘要
本文利用人工神经元网络原理设计了一神经元网络,进行了光谱识别实验,当训练光谱与待识别光谱具有相同的定标情形下,网络具有较高的识别率,可以实用。
An artificial neural network was devised and established for spectral matching.It was proved that when training sample spectra and unknown spectra had the same magnitude calibration,the network recognized spectra very well and had some advantages over other conventional spectral matching methods.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
1999年第2期158-160,共3页
Spectroscopy and Spectral Analysis
关键词
光谱识别
识别
成像光谱仪
遥感
人工神经网络
Spectrum, Imaging spectrometer, Remote sensing, Artificial neural network