EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Baseline Study of End-to-End CNN Models for Paddy Leaf Disease Classification Using Extended Datasets

Lele Mohammed, Aminu Aliyu Abdullahi

International Journal of Smart Agriculture · 2025

DOI: 10.54536/ijsa.v3i1.6188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Smart Agriculture, 2025. Verfasst von Lele Mohammed und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Classification of plant leaf diseases is one of the interesting areas of study in machine learning. Prompt identification and treatment of paddy plant diseases can boost rice production across the world. Rice is one of the major staple food that is consumed worldwide. Its production needs to be enhanced significantly. Rice farmers suffer a great deal by means manual detection of the type of diseases that infect their farmlands. Deploying technology can greatly help farmers to tackle problem of paddy diseases. Convolutional Neural Network (CNN) is an image processing method that can be useful in ensuring higher rice production. The CNN model was used to carry out this research owing to its uniqueness in producing higher detection accuracy. This research work is crucial for its importance in making sure rice crops are cultivated in large scale throughout the world. Four classes of rice diseases are selected for this research, namely: Bacterial leaf blight, rice leaf blast, Tungro and rice brownspot. Although the rice disease dataset is not easily available, this research used datasets of about 5932 images to experiment with CNN on more datasets. The proposed model has achieved an improved accuracy of 99.12% from the benchmark paper.

Zitieren

APA

Mohammed, L., & Abdullahi, A. A. (2025). A Baseline Study of End-to-End CNN Models for Paddy Leaf Disease Classification Using Extended Datasets. International Journal of Smart Agriculture. https://doi.org/10.54536/ijsa.v3i1.6188

Vancouver

Mohammed L, Abdullahi AA. A Baseline Study of End-to-End CNN Models for Paddy Leaf Disease Classification Using Extended Datasets. International Journal of Smart Agriculture. 2025. doi:10.54536/ijsa.v3i1.6188

BibTeX
@article{Mohammed2025,
  author = {Mohammed, Lele and Abdullahi, Aminu Aliyu},
  title = {A Baseline Study of End-to-End CNN Models for Paddy Leaf Disease Classification Using Extended Datasets},
  journal = {International Journal of Smart Agriculture},
  year = {2025},
  doi = {10.54536/ijsa.v3i1.6188}
}
Kostenlos starten →