Coconut Disease Prediction System Using Image Processing and Deep Learning Techniques

Coconut cultivation is a critical component of tropical agriculture, and the early detection of leaf diseases is essential for ensuring plant health and maximizing yield. This project proposes an intelligent Coconut Disease Prediction System using image processing and deep learning techniques. A hybrid model combining MobileNet and EfficientNet architectures is employed to classify coconut leaf images with high accuracy and efficiency. Utilizing transfer learning, the model is trained to automatically detect and categorize leaf conditions into six distinct classes: Healthy_Leaves, CCI_Leaflets, CCI_Caterpillars, WCLWD_Flaccidity, WCLWD_DryingofLeaflets, and WCLWD_Yellowing. These categories cover a range of common coconut leaf health issues, allowing the system to provide precise diagnostics for timely intervention. The model is integrated into a Flask-based web application that enables users to upload images and receive immediate feedback, making the system practical for real-world agricultural monitoring. This automated and scalable solution reduces the need for manual inspection, supports proactive disease management, and contributes to improved crop productivity and sustainability. 

      Keywords: Coconut disease detection, MobileNet, EfficientNet, deep learning, image classification, CNN, transfer learning, plant health, automated diagnosis, sustainable agriculture, agricultural AI