Cargando…

Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning

[Image: see text] Rice is one of the most important food crops in the world, and rice seed varieties are related to the yield and quality of rice. This study used near-infrared (NIR) hyperspectral technology with conventional machine learning methods (support vector machine (SVM), logistic regressio...

Descripción completa

Detalles Bibliográficos
Autores principales: Jin, Baichuan, Zhang, Chu, Jia, Liangquan, Tang, Qizhe, Gao, Lu, Zhao, Guangwu, Qi, Hengnian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8851633/
https://www.ncbi.nlm.nih.gov/pubmed/35187294
http://dx.doi.org/10.1021/acsomega.1c04102
_version_ 1784652861390454784
author Jin, Baichuan
Zhang, Chu
Jia, Liangquan
Tang, Qizhe
Gao, Lu
Zhao, Guangwu
Qi, Hengnian
author_facet Jin, Baichuan
Zhang, Chu
Jia, Liangquan
Tang, Qizhe
Gao, Lu
Zhao, Guangwu
Qi, Hengnian
author_sort Jin, Baichuan
collection PubMed
description [Image: see text] Rice is one of the most important food crops in the world, and rice seed varieties are related to the yield and quality of rice. This study used near-infrared (NIR) hyperspectral technology with conventional machine learning methods (support vector machine (SVM), logistic regression (LR), and random forest (RF)) and deep learning methods (LeNet, GoogLeNet, and residual network (ResNet)) to establish variety identification models for five common types of rice seeds. Among the deep learning methods, the classification accuracies of most models were higher than 95%. This study further used the deep learning methods to establish variety identification models for 10 varieties of rice seeds without considering their types. Among them, the ResNet model had the best classification results. The classification accuracy on the test set was 86.08%. This study used the saliency map method to visualize each convolutional neural network (CNN) model to find the band region that contributed the most to the data. The results showed that the bands with the largest data contribution were mainly concentrated at approximately 1300–1400 nm and secondarily concentrated at approximately 1050–1250 nm. The overall results showed that NIR hyperspectral imaging technology combined with deep learning could effectively distinguish rice seeds of different varieties. This method provided an effective way to identify rice seed varieties in a quick and nondestructive manner.
format Online
Article
Text
id pubmed-8851633
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-88516332022-02-18 Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning Jin, Baichuan Zhang, Chu Jia, Liangquan Tang, Qizhe Gao, Lu Zhao, Guangwu Qi, Hengnian ACS Omega [Image: see text] Rice is one of the most important food crops in the world, and rice seed varieties are related to the yield and quality of rice. This study used near-infrared (NIR) hyperspectral technology with conventional machine learning methods (support vector machine (SVM), logistic regression (LR), and random forest (RF)) and deep learning methods (LeNet, GoogLeNet, and residual network (ResNet)) to establish variety identification models for five common types of rice seeds. Among the deep learning methods, the classification accuracies of most models were higher than 95%. This study further used the deep learning methods to establish variety identification models for 10 varieties of rice seeds without considering their types. Among them, the ResNet model had the best classification results. The classification accuracy on the test set was 86.08%. This study used the saliency map method to visualize each convolutional neural network (CNN) model to find the band region that contributed the most to the data. The results showed that the bands with the largest data contribution were mainly concentrated at approximately 1300–1400 nm and secondarily concentrated at approximately 1050–1250 nm. The overall results showed that NIR hyperspectral imaging technology combined with deep learning could effectively distinguish rice seeds of different varieties. This method provided an effective way to identify rice seed varieties in a quick and nondestructive manner. American Chemical Society 2022-01-31 /pmc/articles/PMC8851633/ /pubmed/35187294 http://dx.doi.org/10.1021/acsomega.1c04102 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Jin, Baichuan
Zhang, Chu
Jia, Liangquan
Tang, Qizhe
Gao, Lu
Zhao, Guangwu
Qi, Hengnian
Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title_full Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title_fullStr Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title_full_unstemmed Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title_short Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning
title_sort identification of rice seed varieties based on near-infrared hyperspectral imaging technology combined with deep learning
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8851633/
https://www.ncbi.nlm.nih.gov/pubmed/35187294
http://dx.doi.org/10.1021/acsomega.1c04102
work_keys_str_mv AT jinbaichuan identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT zhangchu identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT jialiangquan identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT tangqizhe identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT gaolu identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT zhaoguangwu identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning
AT qihengnian identificationofriceseedvarietiesbasedonnearinfraredhyperspectralimagingtechnologycombinedwithdeeplearning