A REAL-TIME MONITORING SYSTEM FOR ACCURATE PLANT LEAVES DISEASE DETECTION USING DEEP LEARNING

Abstract

Accurate and timely detection of plant diseases is crucial for sustainable agriculture and food security. This research presents a real-time monitoring system utilizing deep learning techniques to detect diseases in plant leaves with high accuracy. We combined several plant datasets, including the PlantVillage Dataset, resulting in a comprehensive dataset of 30,945 images across eight plant types (potato, tomato, pepper bell, apple, corn, grape, peach, and rice) and 35 disease classes. Initially, a custom Convolutional Neural Network (CNN) model was developed, achieving a leaf classification accuracy of 95.62%. Subsequently, the dataset was partitioned for individual plant disease detection, applying nine different CNN models (custom CNN, VGG16, VGG19, InceptionV3, MobileNet, DenseNet121, Xception, and two hybrid models) to each plant type. The highest accuracy rates for disease detection were: 100% for potato (custom CNN), 98% for tomato (InceptionV3, custom CNN, VGG16), 100% for pepper bell (MobileNet, custom CNN), 100% for apple (MobileNet, Xception), 98% for corn (custom CNN), 99% for grape (custom CNN, VGG19, DenseNet121), 100% for peach (VGG16, custom CNN), and 98% for rice (DenseNet121). A web and mobile application were developed based on the best-performing models, allowing users to insert or capture images of plant leaves, detect diseases, and receive treatment suggestions with high confidence levels. The results demonstrate the effectiveness of deep learning models in accurately identifying plant diseases, offering a valuable tool for enhancing disease management and crop yields.