ITDS | SPMS

TOMATO DISEASE DETECTION USING CONVOLUTIONAL NEURAL NETWORKS

Project Description
Supervisor

Tomatoes are one of the most widely grown plants in the world. They are susceptible to ravaging diseases like late blight, bacterial spot, and tomato yellow leaf curl virus. The diseases have the potential to reduce crop yield and quality substantially, which jeopardizes the livelihood of farmers. Early and precise detection is crucial for efficient disease control, yet conventional practices such as manual inspection are not only time-consuming, error-prone, and dependent on expertise. The objective of this project is to create a mobile application for the automatic detection of tomato leaf diseases based on Convolutional Neural Networks (CNNs). CNNs have been very successful at image recognition and have also recently demonstrated potential in agriculture. (Elhassouny and Smarandache et al., 2019) showed that tiny CNNs, viz., MobileNet, can diagnose ten tomato leaf diseases on smartphones, with real-time processing. Building on these enhancements, (Attallah et al., 2023) built a transfer learning- and hybrid feature selection-based small CNN pipeline with classification accuracies over 99%. The proposed app combines the above methods in offering a low-cost, efficient, and effective diagnostic app for farmers. It enables the user to capture and diagnose photos of leaves using a smartphone, achieving instant disease diagnosis without special equipment or expertise. With a simple interface, offline capability, and real-time feedback, the app is intended to assist farmers in places with less resources. The long term objective of this project is to improve tomato disease management, minimize crop losses, and ensure sustainable agriculture. With the help of CNN-supported mobile technology it helps to enhance food security and supports farming communities globally.

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.