<![CDATA[Durian is one of Indonesia’s leading horticultural commodities, but its productivity can decline due to leaf diseases that are difficult for farmers to identify visually. This study aims to develop an automated durian leaf disease classification system using a deep learning algorithm based on the ResNet-50 architecture. The dataset consists of 420 durian leaf images classified into four categories: Algal Leaf Spot, Leaf Blight, Leaf Spot, and No Disease, collected from the Roboflow platform. Preprocessing steps included annotation, augmentation, and resizing the images to 240x240 pixels.The model was trained using TensorFlow with pretrained ImageNet weights. Three data split scenarios (70:20:10, 75:15:10, and 80:10:10) were applied using both binary and multiclass classification approaches. Model performance was evaluated using confusion matrix and metrics such as accuracy, precision, recall, and F1-score. The best binary classification result achieved 99.8% accuracy and 99.9% F1-score, while the best multiclass result achieved 99.6% accuracy and 96.9% macro F1-score. These results demonstrate that ResNet-50 is effective in accurately detecting durian leaf diseases and can be implemented in mobile applications to assist farmers in early diagnosis and improving crop productivity.]]>
Copyrights © 2025
