A High-Performance EfficientNetV2-M Model for Robust Corn Leaf Disease Classification
International Journal of Communication Systems and Network Technologies · 31.12.2025 · 14 (3) · 158-168
DOI: 10.18486/ijcsnt/14.3.014 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Communication Systems and Network Technologies, online erschienen am 31.12.2025. Verfasst von Pratham Kaushik. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Corn leaf infections are highly yield-reducing and need to be diagnosed for effective field management. This study proposes a deep learning-based corn leaf disease detection framework based on EfficientNetV2-M, in a transfer learning setting. A structured preprocessing pipeline was used, which involved image resizing (480 × 480 pixels), contrast enhancement with CLAHE in LAB color space, and ImageNet-based normalization for matching inputs with pre-trained weights. The data set was successfully collected from the existing 4,226 field-acquired images of corn leaves categorized into Healthy and Infected classes and divided into training, validation, and testing data samples with stratified sampling. The model was trained for 22 epochs and had an overall test accuracy of 91%. Performance analysis revealed good class-wise metrics, with a precision/recall score of 0.92/0.87 for healthy leaves and 0.89/0.93 for infected leaves. The confusion matrix showed a low level of misclassification, which confirmed the effectiveness of generalization under realistic conditions. The results show that efficientNetV2-M offers an accurate and scalable approach for automated screening of corn leaf disease, enabling precision agriculture and early intervention strategies.
Zitieren
APA
Kaushik, P. (2025). A High-Performance EfficientNetV2-M Model for Robust Corn Leaf Disease Classification. International Journal of Communication Systems and Network Technologies, 14(3), 158-168. https://doi.org/10.18486/ijcsnt/14.3.014
Vancouver
Kaushik P. A High-Performance EfficientNetV2-M Model for Robust Corn Leaf Disease Classification. International Journal of Communication Systems and Network Technologies. 2025;14(3):158-168. doi:10.18486/ijcsnt/14.3.014
BibTeX
@article{Kaushik2025,
author = {Kaushik, Pratham},
title = {A High-Performance EfficientNetV2-M Model for Robust Corn Leaf Disease Classification},
journal = {International Journal of Communication Systems and Network Technologies},
year = {2025},
volume = {14},
number = {3},
pages = {158--168},
doi = {10.18486/ijcsnt/14.3.014}
}
EUVIMED