A Hybrid Approach based on Metaheuristics and Machine Learning for Tomato Plant Leaf Disease Classification

Our energy comes from plants. Plant diseases endanger food security, thus this study focuses on them. Traditional farming is manual, therefore professionals test each plant for host disease. Agriculture is important to India's economy. Pests and diseases kill 15.7% of crops yearly. Virus lowers crop quality and productivity. Correctly detecting and treating the infection will save the plant. Human eyes can't see infected leaf changes. This Paper detects and classifies tomato plant leaf illnesses. This paper shows the use of Metaheuristic-optimized Machine Learning system in categorizing tomato plant leaf diseases in real life, providing useful information for tomato plant maintenance. Metaheuristics solve feature optimization difficulties. This study contrasts supervised machine learning with image processing to establish the best plant disease classification method. Our experiment found that an Equilibrium optimizer combined with Random Forest Classifier has 88.26% accuracy in Tomato Plant Leaf Disease Classification.