AUTOMATED IDENTIFICATION OF TEA LEAF DISEASES AND PESTS USING DEEP LEARNING METHODS

Abstract

Tea is a significant crop and deeply loved by individuals. In earlier times, the identification of tea leaf diseases and pests was manual and inefficient. With the increasing application of AI (artificial intelligence), deep learning and image recognition technology in the field of agriculture, this paper introduces a method with improved efficiency and precision for intelligent identification in tea leaf diseases and pests. We applied the deep learning target detection model, which is the recent version of YOLO (You Only Look Once), specifically YOLOv10s, for automated recognition of tea leaf diseases and pests. This research primarily involves three models: YOLOv8s, YOLOv9s, and YOLOv10s. After training and validation, we conducted a comprehensive performance evaluation and comparative analysis of these models. The comparison of performance metrics indicated that the model based on YOLOv10s performed the best. As shown by the test evaluation results, precision, recall, mAP50 (mean of Average Precision), F1-Score, these values are all higher than those achieved by YOLOv8s and YOLOv9s. Using the optimal YOLOv10s model, combined with the PyQt5 library, a tea leaf diseases and pests target detection recognition interface was developed. Based on this proposed model with YOLOv10s, the identification of tea leaf diseases and pests will be significantly improved for all the terms of higher efficiency, less costs, as well as enhanced quality and sustainability of tea production.

Keywords

• Tea leaf diseases and pests
• Deep learning
• Image recognition technology
• YOLOv10s
• PyQt5