Tomato leaf and Fruit decease

This project proposes an advanced deep learning-based system for the detection and classification of tomato leaf and fruit diseases using image analysis. It integrates two distinct modules: one for leaf disease classification and another for fruit disease detection. For tomato leaf disease classification, we utilize convolutional neural network architectures including MobileNet, CNN, and ResNet to classify ten categories of leaf conditions such as Tomato Mosaic Virus, Target Spot, Bacterial Spot, Tomato Yellow Leaf Curl Virus, Late Blight, Leaf Mold, Early Blight, Spider Mites (Two-Spotted Spider Mite), Tomato Healthy, and Septoria Leaf  Spot. The dataset is sourced from Kaggle's Tomato Leaf dataset to train and validate the models. In the fruit disease detection module, we employ object detection algorithms YOLOv8 and YOLOv9 to accurately identify tomato fruit diseases with bounding boxes. The system is trained on the Rotoflow Tomato Fruit Disease Detection dataset, and it can detect diseases such as Anthracnose, Bacterial Spot, Blossom End Rot, Spotted Wilt Virus, and also identify Healthy Tomato fruits. The application is deployed as a web-based system, developed with a Python backend and a frontend using HTML, CSS, and JavaScript, allowing users to upload images and receive real-time disease predictions. By automating plant disease detection, the system aims to support farmers and agronomists with timely and accurate diagnostics, leading to better crop management and reduced agricultural losses.

Keywords

Tomato Leaf Disease Detection, Fruit Disease Detection, YOLOv8, YOLOv9, MobileNet, CNN, ResNet, Deep Learning, Object Detection, Smart Agriculture, Plant Pathology, Python, Web Application, Image Classification.