Identification of Tomato Leaf Disease using YOLOv8 Detection Models on GPU and Raspberry Pi

Abstract

The paper explores the automated identification of tomato leaf diseases using YOLOv8 detection models on both GPU and Raspberry Pi hardware. Through convolutional neural networks (CNNs) and transfer learning techniques, the study analyzes a dataset comprising images across 10 disease classes. Results demonstrate 0.78-0.79 precision and 0.75-0.81 recall scores for the YOLOv8 models. The Nano model processes single inference on Raspberry Pi in 0.7 second, making it suitable for real-time applications. Through experimental validation, the research underscores the practical significance of deep learning methods in agricultural practices, particularly in greenhouse monitoring and crop management, contributing to early disease detection and ensuring food security.