Automated tomato disease detection and classification using image processing and machine learning for precision agriculture

Abstract

Research aims to diagnose tomato leaf disease using Color Moments, capturing Mean, Standard Deviation, and Skewness. Photos of leaves with Septoria Leaf Spot, Early Blight, and Late Blight undergo feature extraction and segmentation. Color Moments from various channels distinguish infected from healthy leaves, advancing automated disease recognition. The approach, leveraging machine learning and image processing, enables accurate, early diagnosis crucial for disease control. It underscores Color Moments' adaptability for photo indexing and sets a framework for categorizing plant ailments. This technology's development highlights the importance of image-based methodologies in plant pathology, promising enhanced automation and accuracy in disease diagnosis.