<![CDATA[You Only Look Once (YOLO) is an effective deep learning method for real-time object detection. This method is applied to build an accurate, fast facial recognition model, with a case study on an attendance system based on facial images at the Lhokseumawe State Polytechnic. The main objective is to implement and evaluate the YOLOv5s model's performance on the attendance system using facial images with high accuracy. The research process includes collecting facial image datasets from 40 subjects with various viewing angles to train the YOLOv5s model. This model is specifically configured to detect one class of objects, namely faces, and then integrated into the system to function as the main face detector. Model performance is evaluated quantitatively using a confusion matrix to measure key metrics such as accuracy, precision, recall, and F1 score. The evaluation results show that the developed YOLOv5s model has excellent performance. This model achieved 90% accuracy, with a precision and recall of 92%. The balanced F1-score value (92%) proves that the YOLOv5s method has a high level of accuracy for detecting faces. The high-performance metrics confirm that this method is the right solution for building an attendance system based on accurate facial images.]]>
Copyrights © 2026
