核农学报2013，Vol.27Issue(7)：957-961,5.
玉米种子活力近红外光谱智能检测方法研究
Research On Maize Vigor Intelligent Detection Based On Near Infrared Spectroscopy
摘要
Abstract
In order to realize rapid nondestructive recognition of maize vigor,a maize vigor intelligent detection model was put forward by combining NIR and BP neural network.At first,test samples were aged into 3 grades by artificial aging,and near infrared spectroscopy of which was collected.Savitzky-Golay and MSC were used respectively and together to filter noise and wipe off singular spectrum.Principal component analysis (PCA) and discrete wavelet transform (DWT) were respectively used to extract spectral features which act as the input of BP neural network and 6 models were constructed according to preprocessing and feature extraction.The results showed the model which (S-G) + MSC preprocessing was combined with PCA feature extraction was the best:its accuracy rate was 95.0％ and its average identification time is 26.25ms.This investigation provides the theoretical support and practical method for rapid nondestructive recognition of maize vigor.关键词
近红外光谱/主成分分析/离散小波变换/BP神经网络/玉米/种子活力Key words
Near Infrared Spectroscopy/ Principal component analysis/ Discrete wavelet transform/BP neural network/Maize / Seed vigor引用本文复制引用
杨冬风,尹淑欣,姜丽,高树仁..玉米种子活力近红外光谱智能检测方法研究[J].核农学报,2013,27(7):957-961,5.基金项目
农业部引进国际先进农业科学技术计划"948计划"(2008-Z24),黑龙江省教育厅科学技术研究项目(12531468) （2008-Z24）
