Cargando…

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 aver...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Susu, Zhou, Lei, Zhang, Chu, Bao, Yidan, Wu, Baohua, Chu, Hangjian, Yu, Yue, He, Yong, Feng, Lei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6807262/
https://www.ncbi.nlm.nih.gov/pubmed/31547118
http://dx.doi.org/10.3390/s19194065
_version_ 1783461694643634176
author Zhu, Susu
Zhou, Lei
Zhang, Chu
Bao, Yidan
Wu, Baohua
Chu, Hangjian
Yu, Yue
He, Yong
Feng, Lei
author_facet Zhu, Susu
Zhou, Lei
Zhang, Chu
Bao, Yidan
Wu, Baohua
Chu, Hangjian
Yu, Yue
He, Yong
Feng, Lei
author_sort Zhu, Susu
collection PubMed
description 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.
format Online
Article
Text
id pubmed-6807262
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68072622019-11-07 Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network Zhu, Susu Zhou, Lei Zhang, Chu Bao, Yidan Wu, Baohua Chu, Hangjian Yu, Yue He, Yong Feng, Lei Sensors (Basel) Article 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. MDPI 2019-09-20 /pmc/articles/PMC6807262/ /pubmed/31547118 http://dx.doi.org/10.3390/s19194065 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhu, Susu
Zhou, Lei
Zhang, Chu
Bao, Yidan
Wu, Baohua
Chu, Hangjian
Yu, Yue
He, Yong
Feng, Lei
Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title_full Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title_fullStr Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title_full_unstemmed Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title_short Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network
title_sort identification of soybean varieties using hyperspectral imaging coupled with convolutional neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6807262/
https://www.ncbi.nlm.nih.gov/pubmed/31547118
http://dx.doi.org/10.3390/s19194065
work_keys_str_mv AT zhususu identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT zhoulei identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT zhangchu identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT baoyidan identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT wubaohua identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT chuhangjian identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT yuyue identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT heyong identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork
AT fenglei identificationofsoybeanvarietiesusinghyperspectralimagingcoupledwithconvolutionalneuralnetwork