Tomato Leaf Disease Prediction and Classification using Deep Neural Network (DNN)

Farming assumes an essential part in guaranteeing worldwide food security and supporting economies. Predicting tomato leaf diseases is a vital field of study, aimed at preventing significant crop losses caused by various plant diseases. Early and accurate detection plays a crucial role in boosting agricultural productivity, reducing losses, and limiting the use of pesticides. This research investigates how deep learning (DL) can be applied to create predictive models for identifying various diseases in tomato plants. Using image processing and computer vision, the designed modeles are analyse the visible symptoms on tomato leaves, enabling automated, real-time diagnosis of diseases. The study emphasizes improving prediction accuracy, ensuring scalability, and maintaining robustness across different environmental conditions. Plant Village Dataset is considered in this research. By developing affordable and user-friendly tools, this research seeks to help farmers better manage plant diseases and promote sustainable agricultural practices. Our proposed model Deep Neural Network (DNN) achieved an accuracy of 98.17%. The results highlight the transformative potential of AI-driven approaches to revolutionize disease detection and enhance agricultural outcomes. The developed algorithms are very robust, effective and helps in automated seizure detection.