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

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

Abstract


False seeds can often be seen in the maize seed market, leading to a serious decline in maize yield. Those existing variety identification methods are expensive, time consuming, and destructive to seeds. The 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 chemometrics. Because 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 sorting. The 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 models. The environmental factors such as producing areas and years have a significant influence on the performance of the models. Therefore, the method to improve the robustness of the models was investigated in this study. New indexes (correct acceptance degree (CAD), correct rejection degree (CRD) and correct degree (CD)) were defined to analyze the performance of the models more accurately. Finally, the models obtained a mean correct discrimination rate of over 90%, and exhibited robust properties for samples harvested from different areas and years. The 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.
Keywords: maize, seed variety identification, near-infrared reflectance spectroscopy (NIRS), biomimetic pattern recognition (BPR)
DOI: 10.25165/j.ijabe.20181102.2815

Citation: Cui Y J, Xu L J, An D, Liu Z, Gu J C, Li S M, et al. Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics. Int J Agric & Biol Eng, 2018; 11(2): 177–183.

Keywords


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

Full Text:

PDF

References


He K Q, Cheng X X. The analysis of esterase isozyme in different maize species. Chinese Agricultural Science Bulletin, 2008; 4(24): 221. (in Chinese)

Sharopova N, McMullen M D, Schultz L, Schroeder S, Sanchez-Villeda H, Gardiner J, et al. Development and mapping of SSR markers for maize. Plant Mol. Biol., 2002; 48: 463.

Zhao J R, Sun S X, Wang F G. Research trends in China maize variety identification by DNA fingerprinting. Beijing: China Agricultural Science and Technology Press, 2008.

Yan Y L, Zhao L L, Han D H, Yang S M. Basics and application of near

infrared spectral analysis. Beijing: China Light Industry Press, 2005; 38p.

Zhou J, Cheng H, Ye Y, Wang L Y, He W, Liu X, et al. Recognition for raw material cultivar of manufactured tea with fisher discriminant classification with principal components analysis. Acta Optica Sinica, 2009; 29(4): 1117–1120. (in Chinese)

Liang L, Liu Z X, Yang M H, Zhang Y X, Wang C H. Discrimination of variety and authenticity for rice based on visual/near infrared reflection spectra. Journal of Infrared and Millimeter Waves, 2009; 28(5): 353–356. (in Chinese)

Cao F, Wu D, He Y, Bao Y D. Variety discrimination of grapes based on visible-near reflection infrared spectroscopy. Acta Optica Sinica, 2009; 29(2): 537–540. (in Chinese)

Zhuang X G, Wang L L, Wu X Y, Fang J X. Origin identification of Shandong green tea by moving window back propagation artificial neural network based on near infrared spectroscopy. Journal of Infrared and Millimeter Waves, 2016; 35(2): 200–204.

Han Z Z, Wan J H, Zhang H S, Deng L M, Du H W, Yang J Z. Variety and origin identification of maize based on near infrared spectrum. Journal of the Chinese Cereals and Oils Association, 2014; 29(1): 21–24. (in Chinese)

Liu X. Research of automatic maize seed purity sorting system. Beijing: China Agricultural University, 20115; pp.0–13. (in Chinese)

Zhao S Y. Study on the influence of different producing places and years for the maize seeds purity sorting. Beijing: China Agricultural University, 2016; pp.17–21. (in Chinese)

Zhao H Y, Guo B L, Wei Y M, Zhang B. Near infrared reflectance spectroscopy for determination of the geographical origin of wheat. Food Chemistry, 2013; 138: 1902–1907.

Wang S J, Wang B N. Analysis and theory of high-dimension space geometry for artificial neural networks. Acta Electronica Sinica, 2002; 30: 1417. (in Chinese)

Wang S J, Liu Y Y, Lai J L, Liu X X. Biomimetic pattern recognition and multi-weighted neuron. Beijing: National Defence Industry Press, 2013; 156p.

Guo T T. Study on the cultivar discrimination method for maize seeds based on near infrared spectroscopy and biomimetic pattern recognition. Beijing: Institute of Semiconductors, Chinese Academy of Sciences, 2010. (in Chinese)

Agelet L E, Hurburgh C R. Limitations and current applications of near infrared spectroscopy for single seed analysis. Talanta, 2014; 121: 288.

Jia S Q, Guo T T, Tang X T, Si G, Yan Y L, An D. Study on spectral measurement methods in identification of maize variety authenticity based on near-infrared spectra of single kernels. Spectroscopy and Spectra Analysis, 2012; 32: 103. (in Chinese)

Guo T T, Wu W J, Su Q, Wang S J, An D. Effects of spectral pretreatment and wavelength selection on discrimination of maize seed varieties by NIR spectroscopy. Transactions of the CSAM. 2009; 40(Supp l): 87. (in Chinese)

Cocchi M, Corbellini M, Foca G, Lucisano M, Pagani MA, Tassi L, et al. Classification of bread wheat flours in different quality categories by a wavelet-based feature selection/classification algorithm on NIR spectra. Anal. Chim. Acta, 2005; 544: 100.

Janni J. Pioneer Hi-Bred International Inc. Patent 7274457 B2, 2007.

Janni J, Weinstock B A, Hagen L, Wright S. Novel near-infrared sampling apparatus for single kernel analysis of oil content in maize. Appl. Spectrosc, 2008; 62(4): 423.

Armstrong P R. Rapid single-kernel NIR measurement of grain and oil-seed attributes. Appl. Eng. Agric, 2006; 22(5): 767.




Copyright (c)



2023-2026 Copyright IJABE Editing and Publishing Office