DESIGN OF A SMART SYSTEM REAL-TIME TOMATO LEAF DISEASE DETECTION SYSTEM FOR SUSTAINABLE AGRICULTURAL DEVELOPMENT IN BAUCHI NIGERIA
Abstract
ABSTRACT
The design and implementation of a Smart System real-time tomato leaf disease detection system aimed at promoting sustainable agricultural development in Bauchi, Nigeria. Tomato production is often threatened by leaf diseases such as Early Blight, Late Blight, Target Spot, and Spider Mites, which reduce yield and quality. The Smart system integrates a Convolutional Neural Network (CNN) with to provide accurate and timely disease diagnosis. The CNN model was trained on the PlantVillage dataset, with preprocessing techniques including image resizing, normalization, and data augmentation to enhance accuracy and generalization. Farmers can upload leaf images or capture live photos via System-enabled cameras through a web-based interface developed using Python and Flask, receiving instant classification results along with recommended management practices. The system was evaluated in both online modes, achieving over 96% accuracy in disease detection. By combining smart System and deep learning technologies, this solution offers a cost-effective, scalable, and user-friendly tool for real-time monitoring, enabling farmers to make informed decisions, reduce tomato losses, and support sustainable agriculture in Bauchi Nigeria.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.