Answers are grounded in this paper and cite their sources.
The agricultural sector increasingly relies on advanced technologies to enhance productivity and address challenges in disease management. In this context, deep learning-based image processing techniques play a crucial role in detecting diseases in tomato fruits. The aim of this research is to evaluate the performance of the YOLOv8 model in agricultural disease detection by comparing it with the YOLOv5 model. The results show that YOLOv8 outperforms YOLOv5 in detecting diseased tomatoes with higher accuracy (98.0% vs. 97.2%), precision (97.5% vs. 96.8%), recall (98.5% vs. 97.6%), and F1 score (97.8% vs. 97.0%). YOLOv8 also has a shorter inference time (35 ms vs. 45 ms). In detailed performance comparisons by disease type, YOLOv8 demonstrated superior results, particularly in “Early Blight,” with 99.0% accuracy and a 98.8% F1 score. In conclusion, YOLOv8 offers significant advantages in performance, speed, and training time for agricultural disease detection. These strengths have the potential to boost productivity and minimize losses through early disease detection and intervention. Furthermore, this research highlights that the success of deep learning models heavily depends on the quality and quantity of labeled data and provides valuable insights for the future development of agricultural disease detection technologies.
No takes yet. Share an insight, caveat, or question.
Özel et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: