您好，欢迎访问浙江省农业科学院 机构知识库！
浙江省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

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

文献类型： 外文期刊

作者： Yang, Yong 1 ; Chen, Jianping 1 ; He, Yong 3 ; Liu, Feng 4 ; Feng, Xuping 3 ; Zhang, Jinnuo 3 ;

作者机构： 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

期刊名称：RSC ADVANCES （ 影响因子：3.361； 五年影响因子：3.39 ）

ISSN：

年卷期： 2020 年 10 卷 72 期

页码：

收录情况： SCI

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.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：浙江省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台