Detection system of disease from tomato leaf using convolutional neural network / Nurkhairunnisa’ Azhan and Hajar Izzati Mohd Ghazalli

Tomato farming is crucial for global food production, but diseases affecting tomato plants can harm crop quality and lead to economic losses for farmers. Many farmers lack expertise and education in identifying these diseases, highlighting the need for accessible tools. This study focused on creating a user-friendly web-based system using Convolutional Neural Networks (CNN) to detect tomato leaf diseases. The goal was to empower farmers with a convenient and efficient platform to identify and address diseases, automating the detection process and reducing reliance on manual analysis. The system, achieving over 92.5% accuracy, aimed to enhance productivity by providing timely and accurate identification of tomato leaf diseases. Farmers could easily monitor and assess plant infections through the web-based platform. The research outcomes are expected to benefit the agricultural community by offering a valuable tool for informed decision- making, leading to improved crop quality and increased productivity. Future improvements could include additional functions and information for users, as well as expanding the system to detect more types of tomato leaf diseases.