EUVIMEDEUVIMED entdecken
Crossref

Deep recognition of rice disease images: how many training samples do we really need?

Huiru Zhou, Dong Huang, Bo Ming Wu iD

Journal of the Science of Food and Agriculture · 2024

DOI: 10.1002/jsfa.13636 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Science of Food and Agriculture, 2024. Verfasst von Huiru Zhou und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Plant Protection, South China Agricultural University, Guangzhou, China. Hauptthemen laut MEDLINE: Oryza, Deep Learning, Plant Diseases, Plant Leaves. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND With the rapid development of deep learning, the recognition of rice disease images using deep neural networks has become a hot research topic. However, most previous studies only focus on the modification of deep learning models, while lacking research to systematically and scientifically explore the impact of different data sizes on the image recognition task for rice diseases. In this study, a functional model was developed to predict the relationship between the size of dataset and the accuracy rate of model recognition. RESULTS Training VGG16 deep learning models with different quantities of images of rice blast‐diseased leaves and healthy rice leaves, it was found that the test accuracy of the resulting models could be well fitted with an exponential model ( A = 0.9965 − e (−0.0603×I50−1.6693) ). Experimental results showed that with an increase of image quantity, the recognition accuracy of deep learning models would show a rapid increase at first. Yet when the image quantity increases beyond a certain threshold, the accuracy of image classification would not improve much, and the marginal benefit would be reduced. This trend remained similar when the composition of the dataset was changed, no matter whether (i) the disease class was changed, (ii) the number of classes was increased or (iii) the image data were augmented. CONCLUSIONS This study provided a scientific basis for the impact of data size on the accuracy of rice disease image recognition, and may also serve as a reference for researchers for database construction. © 2024 Society of Chemical Industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OryzaDeep LearningPlant DiseasesPlant LeavesImage Processing, Computer-AssistedNeural Networks, Computer

Stichwörter der Autor:innen

crop disease identificationdata sizedeep learningimage augmentationtransfer learning

Autor:innen und Institutionen

  • College of Plant Protection, South China Agricultural University, Guangzhou, China.
  • College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China.
  • College of Plant Protection, China Agricultural University, Beijing, China.

ORCID-Profile: Bo Ming Wu

Zitieren

APA

Zhou, H., Huang, D., & Wu, B. M. (2024). Deep recognition of rice disease images: how many training samples do we really need?. Journal of the Science of Food and Agriculture. https://doi.org/10.1002/jsfa.13636

Vancouver

Zhou H, Huang D, Wu BM. Deep recognition of rice disease images: how many training samples do we really need?. Journal of the Science of Food and Agriculture. 2024. doi:10.1002/jsfa.13636

BibTeX
@article{Zhou2024,
  author = {Zhou, Huiru and Huang, Dong and Wu, Bo Ming},
  title = {Deep recognition of rice disease images: how many training samples do we really need?},
  journal = {Journal of the Science of Food and Agriculture},
  year = {2024},
  doi = {10.1002/jsfa.13636}
}
Kostenlos starten →