ITDS | SPMS

CLASSIFICATION OF MAIZE PLANT PESTS AND DISEASE INFESTATION USING CONVOLUTIONAL NEURAL NETWORKS

Project Description
Supervisor

Maize is a vital crop for food security for millions of individuals globally. It is under serious threat from diseases and pests like Maize Streak Virus and grasshoppers, which have the potential to bring about enormous yield losses and create issues for food security worldwide. Its effective management demands timely and precise disease detection. Traditional methods of detection are typically time-consuming, slow, and prone to human error. This necessitates automated, precise, and available solutions. This project aims to address these challenges by developing a mobile app that detects maize diseases. The app uses Convolutional Neural Networks (CNNs), a deep learning technique that has been acclaimed for its superior performance in image classification. The main goal is to make the detection process as easy and automated as possible so that farmers and agricultural experts can easily detect the symptoms of diseases using an everyday smartphone. Manual field scouting and machine learning algorithms are some of the current methods applied in maize disease detection, but they both have their limitations. Machine learning algorithms require large volumes of labeled data and large computational resources that might not be available in farm environments where computing resources are limited. This project is intended to offer a fast solution. The user can simply capture images of maize plants using the camera on their phone. The application then processes these images through a CNN-based model, which detects and classifies diseases with a high level of accuracy. This method removes the requirement for any specialized equipment or expert understanding, making it usable by more individuals, such as smallholder farmers. The mobile app features an easy-to-use interface and real-time analysis. This mobile app project represents a huge leap forward in maize disease diagnosis and management. Taking advantage of the capabilities of emerging technology, it overcomes the limitations of current methods in facilitating users' informed decision-making and, ultimately, in backing food security and livelihoods for maize-reliant populations.

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.

To create a simple-to-operate and accessible mobile app for the identification of maize plant pests and diseases using image processing and a convolutional neural network to present precise results

2024/2025

Feb 12, 2026

ACHEAMPONG UWUMBORJA FREDERICK, DAWSON DARKO GIBSON, BAIDEN EUGENIA, EFFAH SILAS, ABDUL-WAHID IBRAHIM

BSc Information Technology