AUTHOR=Qi Hengnian , Huang Zihong , Sun Zeyu , Tang Qizhe , Zhao Guangwu , Zhu Xuhua , Zhang Chu 

TITLE=Rice seed vigor detection based on near-infrared hyperspectral imaging and deep transfer learning

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1283921

DOI=10.3389/fpls.2023.1283921

ISSN=1664-462X

ABSTRACT=Vigor is one of the important factors that affects rice yield and quality. In this study, near-infrared hyperspectral imaging techniques and transfer learning were combined to detect rice seed vigor and improve the generalization ability and robustness of the model. We constructed different convolutional neural network (CNN) models to detect the vigor of four rice seeds (Yongyou12, Yongyou1540, Suxiangjing100, and Longjingyou1212), and used two transfer strategies, fine-tuning and MixStyle, to transfer knowledge to different rice varieties for vigor detection. The experimental results showed that the convolutional neural network model of Yongyou12 classified the vigor of Yongyou1540, Suxiangjing100, and Longjingyou1212 through MixStyle transfer knowledge, and the accuracy reached 90.00%, 80.33%, and 85.00% respectively, which was better or close to the initial modeling level of each variety. MixStyle statistics are based on probabilistic mixed instance-level features of cross-source domain training samples. When training instances, new domains can be synthesized, which increases the domain diversity of the source domain, thereby improving the generalization ability of the trained model.