<![CDATA[Object detection is a critical component in various modern applications, including healthcare systems, smart agriculture, and industrial automation. The main challenge in developing detection systems lies in achieving high accuracy and strong generalization capabilities under diverse image conditions. This study aims to implement and evaluate the YOLOv8 model, a detection method known for its speed and efficiency. The model is trained using two scenarios—10 epochs and 50 epochs—to examine the impact of training duration on system performance. Evaluation results show that training for 10 epochs produces very good performance, with a precision of 0.98, recall of 0.94, and mAP of 0.98. Increasing the training to 50 epochs yields even more optimal results, achieving a precision of 0.99, recall of 1.00, and mAP of 0.99. Based on these findings, YOLOv8 demonstrates excellent adaptability to the dataset and is suitable for real-time detection applications that require high accuracy]]>
Copyrights © 2026
