Crop Disease Detection Using MobileNetV3-Small Convolutional Neural Networks (CNNs) to Support Armenian Agriculture
2025
Asatryan, Hayk
The agricultural sector of Armenia faces many problems, such as low productivity, small landholdings, limited technological machinery, reliance on low-value crops, and inadequate expertise. This article uses Artificial Intelligence (AI), specifically Convolutional Neural Networks (CNNs) based on MobileNetV3-Small architecture, to improve crop disease detection. The model was trained and validated using fruit and berry colored leaf images from the PlantVillage dataset. The final model achieved an accuracy of 99.25% and a macro F1-score of 0.9891 across 13 plant disease and health categories, which indicates the model’s strong potential for accurate crop disease detection.
Show more [+] Less [-]AGROVOC Keywords
Bibliographic information
Publisher Armenian National Agrarian University
ISSN 2579-2822This bibliographic record has been provided by Armenian National Agrarian University