Automated Fusarium Wilt Classification in Plants using VGG16 Architecture

Fusarium wilt, induced by pathogenic fungus,
represents a substantial risk to world agriculture, impacting
several plant species. Timely identification and precise
classification of this disease are essential for optimal care and
control. This research introduces an automated classification
method using the VGG16 deep learning architecture to detect
Fusarium wilt in plants. It collected an extensive dataset of
images of healthy and diseased plant leaves. The VGG16
model, recognized for its depth and feature extraction
proficiency, was fine-tuned and trained on this dataset. The
model's efficacy was assessed using accuracy, precision, recall,
and F1 score. The results indicated that the VGG16
architecture attained superior classification accuracy,
improving conventional approaches. The proposed method
enhances the detection process and offers a dependable
instrument for farmers and agronomists to assess crop health.
This method underscores the promise of deep learning
methods in agricultural applications, facilitating future disease
control and precision agriculture studies. Future efforts will
concentrate on increasing the dataset and including real-time
monitoring functionalities in the system.