Image-based diagnosis of potato leaf diseases using shallow-CNN design
Journal of Biological Regulators and Homeostatic Agents · 17.04.2026 · 40 (2)
DOI: 10.65746/jbrha114 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biological Regulators and Homeostatic Agents, online erschienen am 17.04.2026. Verfasst von Santhana Krishnan Rajan und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Precision agriculture endures significant hurdles in accurately identifying and classifying plant diseases. Since different plant diseases display subtle and varied symptoms, traditional procedures involving manual inspection are time-consuming and result in high false positives. To overcome these obstacles, a lightweight Shallow-CNN classification framework tailored specifically to potato leaf disease was proposed. The proposed framework is further combined with formidable ensemble learning methods, Random Forest and XGBoost, to ensure better classification of potato leaf disease and reduce overfitting. The proposed algorithm was trained and evaluated on the benchmark Plant Village dataset and real-world images taken from the crop fields. The experimental results show that the proposed framework achieves better accuracy, precision, F1-score and recall when compared with several state-of-the-art approaches. This shows that it is particularly effective and scalable for real-time agricultural disease surveillance systems.
Zitieren
APA
Rajan, S. K., & Eanoch, G. J. (2026). Image-based diagnosis of potato leaf diseases using shallow-CNN design. Journal of Biological Regulators and Homeostatic Agents, 40(2). https://doi.org/10.65746/jbrha114
Vancouver
Rajan SK, Eanoch GJ. Image-based diagnosis of potato leaf diseases using shallow-CNN design. Journal of Biological Regulators and Homeostatic Agents. 2026;40(2). doi:10.65746/jbrha114
BibTeX
@article{Rajan2026,
author = {Rajan, Santhana Krishnan and Eanoch, Golden Julie},
title = {Image-based diagnosis of potato leaf diseases using shallow-CNN design},
journal = {Journal of Biological Regulators and Homeostatic Agents},
year = {2026},
volume = {40},
number = {2},
doi = {10.65746/jbrha114}
}
EUVIMED