Abstract:
"This project proposes a novel disease diagnosis ensemble model for detecting tomato plant leaf
diseases using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to
accurately 9 types of diseases affecting tomato leaves with a high level of accuracy. The
proposed ensemble model has shown an accuracy of 96.5% on the PlantsVillage data set from
Kaggle. The ensemble model aims to address the challenges faced bye farmers in accurately and
timely identifying various tomato leaf diseases. By leveraging deep learning techniques and
image processing, the project seeks to develop a user-friendly web application that enables
farmers to upload images of tomato leaves and receive automated disease diagnoses. The
proposed framework will utilize a CNN model and ViT model trained on a diverse dataset of
tomato leaf images, incorporating data augmentation techniques to enhance accuracy and
robustness. The web application will provide farmers with real-time disease identification,
facilitating early intervention and effective disease management strategies.
"
