Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network

Soybean variety is connected to stress resistance ability, as well as nutritional and commercial value. Near-infrared hyperspectral imaging was applied to classify three varieties of soybeans (Zhonghuang37, Zhonghuang41, and Zhonghuang55). Pixel-wise spectra were extracted and preprocessed, and average spectra were also obtained. Convolutional neural networks (CNN) using the average spectra and pixel-wise spectra of different numbers of soybeans were built. Pixel-wise CNN models obtained good performance predicting pixel-wise spectra and average spectra. With the increase of soybean numbers, performances were improved, with the classification accuracy of each variety over 90%. Traditionally, the number of samples used for modeling is large. It is time-consuming and requires labor to obtain hyperspectral data from large batches of samples. To explore the possibility of achieving decent identification results with few samples, a majority vote was also applied to the pixel-wise CNN models to identify a single soybean variety. Prediction maps were obtained to present the classification results intuitively. Models using pixel-wise spectra of 60 soybeans showed equivalent performance to those using the average spectra of 810 soybeans, illustrating the possibility of discriminating soybean varieties using few samples by acquiring pixel-wise spectra.

[1]  Xinjie Yu,et al.  Nondestructive Freshness Discriminating of Shrimp Using Visible/Near-Infrared Hyperspectral Imaging Technique and Deep Learning Algorithm , 2018, Food Analytical Methods.

[2]  G. Bisztray,et al.  Distinguishing melon genotypes using NIR spectroscopy , 2004 .

[3]  D. Fukushima,et al.  Recent progress of soybean protein foods: Chemistry, technology, and nutrition , 1991 .

[4]  F. Below,et al.  Nutrient Uptake, Partitioning, and Remobilization in Modern Soybean Varieties , 2015 .

[5]  Shanjun Mao,et al.  A deep learning framework for hyperspectral image classification using spatial pyramid pooling , 2016 .

[6]  Susanne Jacobsen,et al.  A chemometric evaluation of the underlying physical and chemical patterns that support near infrared spectroscopy of barley seeds as a tool for explorative classification of endosperm genes and gene combinations , 2005 .

[7]  Yong He,et al.  Application of hyperspectral imaging and chemometrics for variety classification of maize seeds , 2018, RSC advances.

[8]  Yingpeng Han,et al.  Identification of quantitative trait loci underlying seed protein content of soybean including main, epistatic, and QTL × environment effects in different regions of Northeast China. , 2017, Genome.

[9]  Chu Zhang,et al.  Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network , 2018 .

[10]  Colm P. O'Donnell,et al.  Hyperspectral imaging – an emerging process analytical tool for food quality and safety control , 2007 .

[11]  Huanda Lu,et al.  Deep-learning-based regression model and hyperspectral imaging for rapid detection of nitrogen concentration in oilseed rape (Brassica napus L.) leaf , 2018 .

[12]  Yibin Ying,et al.  DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis. , 2019, Analytica chimica acta.

[13]  Alberto Signoroni,et al.  Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review , 2019, J. Imaging.

[14]  Wasin Sinthupinyo,et al.  Color and texture for corn seed classification by machine vision , 2011, 2011 International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS).

[15]  R. Galvão,et al.  Classification of individual cotton seeds with respect to variety using near-infrared hyperspectral imaging , 2016 .

[16]  Renato Grimaldi,et al.  Zero trans fats from soybean oil and fully hydrogenated soybean oil: Physico-chemical properties and food applications , 2009 .

[17]  Raymond Y. K. Lau,et al.  Hyperspectral Image Classification With Deep Learning Models , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Elena Marchiori,et al.  Convolutional neural networks for vibrational spectroscopic data analysis. , 2017, Analytica chimica acta.

[19]  P. Tantasawat,et al.  SSR Analysis of Soybean ('Glycine max' (L.) Merr.) Genetic Relationship and Variety Identification in Thailand , 2011 .

[20]  Margarita Ruiz-Altisent,et al.  Monitoring spinach shelf-life with hyperspectral image through packaging films , 2013 .

[21]  Devanand L. Luthria,et al.  Metabolite changes in nine different soybean varieties grown under field and greenhouse conditions. , 2016, Food chemistry.

[22]  J. Blasco,et al.  Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment , 2012, Food and Bioprocess Technology.

[23]  Niraj Tripathi,et al.  SSR analysis of 38 genotypes of soybean (Glycine Max (L.) Merr.) genetic diversity in India , 2014, Physiology and Molecular Biology of Plants.

[24]  Chu Zhang,et al.  Identification of coffee bean varieties using hyperspectral imaging: influence of preprocessing methods and pixel-wise spectra analysis , 2018, Scientific Reports.

[25]  Yidan Bao,et al.  Hyperspectral imaging for seed quality and safety inspection: a review , 2019, Plant Methods.

[26]  P. Cregan,et al.  The use of microsatellite DNA markers for soybean genotype identification , 2004, Theoretical and Applied Genetics.

[27]  Changying Li,et al.  Classification of foreign matter embedded inside cotton lint using short wave infrared (SWIR) hyperspectral transmittance imaging , 2017, Comput. Electron. Agric..

[28]  Suresh N. Mali,et al.  Identification of paddy varieties based on novel seed angle features , 2016, Comput. Electron. Agric..

[29]  Ranjithkumar Nagireddy,et al.  DNA Fingerprinting for Identification of Rice Varieties and Seed Genetic Purity Assessment , 2018, Agricultural Research.

[30]  Gregory L. Tylka,et al.  Increase in Soybean Cyst Nematode Virulence and Reproduction on Resistant Soybean Varieties in Iowa From 2001 to 2015 and the Effects on Soybean Yields , 2017 .

[31]  Chu Zhang,et al.  Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method , 2019, IEEE Access.

[32]  Yonghong He,et al.  Fast and accurate decoding of Raman spectra-encoded suspension arrays using deep learning. , 2019, The Analyst.

[33]  Chu Zhang,et al.  Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging , 2018, Molecules.