Assessment of the vigor of rice seeds by near-infrared hyperspectral imaging combined with transfer learning

被引:16
作者
Yang, Yong [1 ]
Chen, Jianping [1 ,2 ]
He, Yong [3 ,5 ]
Liu, Feng [4 ]
Feng, Xuping [3 ,5 ]
Zhang, Jinnuo [3 ,5 ]
机构
[1] Zhejiang Acad Agr Sci, State Key Lab Managing Biot & Chem Treats Qual &, Inst Virol & Biotechnol,Zhejiang Prov Key Lab Bio, Minist Agr & Rural Affairs,Key Lab Biotechnol Pla, Hangzhou, Peoples R China
[2] Ningbo Univ, State Key Lab Managing Biot & Chem Treats Qual &, Inst Plant Virol,Zhejiang Prov Key Lab Biotechnol, Minist Agr & Rural Affairs,Key Lab Biotechnol Pla, Ningbo, Peoples R China
[3] Zhejiang Univ, Coll Biosyst Engn & Food Sci, Minist Agr & Rural Affairs, Key Lab Spect, Hangzhou, Peoples R China
[4] Nanjing Agr Univ, Coll Life Sci, Nanjing, Peoples R China
[5] Zhejiang Univ, Huanan Ind Technol Res Inst, Guangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
CLASSIFICATION; GERMINATION; QUICK;
D O I
10.1039/d0ra06938h
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Rice seed vigor plays a significant role in determining the quality and quantity of rice production. Thus, the quick and non-destructive identification of seed vigor is not only beneficial to fully obtain the state of rice seeds but also the intelligent development of agriculture by instant monitoring. Thus, herein, near-infrared hyperspectral imaging technology, as an information acquisition tool, was introduced combined with a deep learning algorithm to identify the rice seed vigor. Both the spectral images and average spectra of the rice seeds were sent to discriminant models including deep learning models and traditional machine learning models, and the highest accuracy of vigor identification reached 99.5018% using the self-built model. The parameters of the established deep learning models were frozen to be feature extractor for transfer learning. The identification results whose highest number also reached almost 98% indicated the possibility of applying transfer learning to improve the universality of the models. Moreover, by visualizing the output of convolutional layers, the progress and mechanism of spectral image feature extraction in the established deep learning model was explored. Overall, the self-built deep learning models combined with near-infrared hyperspectral images in the determination of rice seed vigor have potential to efficiently perform this task.
引用
收藏
页码:44149 / 44158
页数:10
相关论文
共 40 条
[31]   Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network [J].
Wu, Na ;
Zhang, Chu ;
Bai, Xiulin ;
Du, Xiaoyue ;
He, Yong .
MOLECULES, 2018, 23 (11)
[32]  
Zhang J., 2020, FRONT PHARMACOL, P11
[33]   Study on Driving Decision-Making Mechanism of Autonomous Vehicle Based on an Optimized Support Vector Machine Regression [J].
Zhang, Junyou ;
Liao, Yaping ;
Wang, Shufeng ;
Han, Jian .
APPLIED SCIENCES-BASEL, 2018, 8 (01)
[34]   Hyperspectral imaging technology combined with deep forest model to identify frost-damaged rice seeds [J].
Zhang, Liu ;
Sun, Heng ;
Rao, Zhenhong ;
Ji, Haiyan .
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, 2020, 229
[35]   Feature Extraction for Classification of Hyperspectral and LiDAR Data Using Patch-to-Patch CNN [J].
Zhang, Mengmeng ;
Li, Wei ;
Du, Qian ;
Gao, Lianru ;
Zhang, Bing .
IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (01) :100-111
[36]   Melatonin promotes water-stress tolerance, lateral root formation, and seed germination in cucumber (Cucumis sativus L.) [J].
Zhang, Na ;
Zhao, Bing ;
Zhang, Hai-Jun ;
Weeda, Sarah ;
Yang, Chen ;
Yang, Zi-Cai ;
Ren, Shuxin ;
Guo, Yang-Dong .
JOURNAL OF PINEAL RESEARCH, 2013, 54 (01) :15-23
[37]  
Zhang ZH, 2019, ANAL METHODS-UK, V11, P5910, DOI [10.1039/C9AY01926J, 10.1039/c9ay01926j]
[38]   Application of Deep Learning in Food: A Review [J].
Zhou, Lei ;
Zhang, Chu ;
Liu, Fei ;
Qiu, Zhengjun ;
He, Yong .
COMPREHENSIVE REVIEWS IN FOOD SCIENCE AND FOOD SAFETY, 2019, 18 (06) :1793-1811
[39]   A Rapid and Highly Efficient Method for the Identification of Soybean Seed Varieties: Hyperspectral Images Combined with Transfer Learning [J].
Zhu, Shaolong ;
Zhang, Jinyu ;
Chao, Maoni ;
Xu, Xinjuan ;
Song, Puwen ;
Zhang, Jinlong ;
Huang, Zhongwen .
MOLECULES, 2020, 25 (01)
[40]   Identifying Freshness of Spinach Leaves Stored at Different Temperatures Using Hyperspectral Imaging [J].
Zhu, Susu ;
Feng, Lei ;
Zhang, Chu ;
Bao, Yidan ;
He, Yong .
FOODS, 2019, 8 (09)