A Deep Learning-Based Intelligent Approach for Automated Olive Leaf Disease Detection Using the Optimized VGG16

Olive leaf diseases significantly impact crop yield and quality, posing a threat to agricultural productivity and economic stability. Traditional disease detection methods are often time-consuming and costly. This study presents an automated deep learning approach for olive leaf disease classification, utilizing the VGG16 architecture with optimized fine-tuning. A dataset of 954 olive leaf images (382 infected, 572 healthy) collected from agricultural fields in Turkey was augmented via rotation, cropping, and flipping to enhance model robustness. The pre-trained VGG16 model was fine-tuned for feature extraction, followed by classification layers incorporating dropout and Softmax activation. Experimental results demonstrated a state-of-the-art classification accuracy of 99.47%, outperforming existing methods. The results confirm the effectiveness of deep learning for agricultural automation, providing a rapid, low-cost solution for early disease detection and management.