Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics

作     者：Yongjin Cui Lanjun Xu Dong An Zhe Liu Jiancheng Gu Shaoming Li Xiaodong Zhang Dehai Zhu 

作者机构：College of Information and Electrical EngineeringChina Agricultural UniversityBeijing 100083China Beijing Agricultural Machinery Experiment Appraisal and Popularization StationBeijing 100079China Key Laboratory of Agricultural Information Acquisition Technology(Beijing)Ministry of AgricultureBeijing 100083China Beijing Kings Nower Seed S&T Co.Ltd.Beijing 100080China 

出 版 物：《International Journal of Agricultural and Biological Engineering》 (国际农业与生物工程学报（英文）)

年 卷 期：2018年第11卷第2期

页      面：177-183页

核心收录：

学科分类：0710[理学-生物学] 0810[工学-信息与通信工程] 09[农学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0901[农学-作物学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key Scientific Instruments and Equipment Development Project(2014YQ470377) National Special Fund for Agro-scientific Research in Public Interest(Grant No.201203052) Science and Technology Project of Beijing(Grant No.D131100000413002) China Agricultural University Education Foundation Dabeinong Education Funds(1081-2413001) 

主　　题：maize seed variety identification near-infrared reflectance spectroscopy(NIRS) biomimetic pattern recognition(BPR) 

摘      要：False seeds can often be seen in the maize seed market,leading to a serious decline in maize *** existing variety identification methods are expensive,time consuming,and destructive to *** aim of this study is to develop a cheap,fast and non-destructive method which can robustly identify large amounts of maize seed varieties based on near-infrared reflectance spectroscopy(NIRS)and *** it is difficult to establish models for every variety in the market,this study mainly investigated the performance of models based on a large number of samples(more than 40 major varieties in the market).The reflectance spectra of maize seeds were collected by two modes(bulk kernels mode and single kernel mode).Both collection modes can be applied to identification,but only the single kernel mode can be applied to purity *** spectra were pretreated with smoothing,the first derivative and vector normalization;and then principal component analysis(PCA),linear discriminant analysis(LDA)and biomimetic pattern recognition(BPR)were applied to establish identification *** environmental factors such as producing areas and years have a significant influence on the performance of the ***,the method to improve the robustness of the models was investigated in this *** indexes(correct acceptance degree(CAD),correct rejection degree(CRD)and correct degree(CD))were defined to analyze the performance of the models more ***,the models obtained a mean correct discrimination rate of over 90%,and exhibited robust properties for samples harvested from different areas and *** results showed that NIR technology combined with chemometrics methods such as PCA,LDA,and BPR could be a suitable and alternative technique to identify the authenticity of maize seed varieties.