<![CDATA[The development of artificial intelligence (AI) technology encourages innovation in image processing and computer vision, one of which is a real-time facial expression detection system. This research aims to develop a system based on the YOLOv5 method and deep learning algorithms to detect facial expressions, such as neutral and smile, with high accuracy. The system is designed using training data processed through Roboflow, including dataset collection, labeling, and augmentation. The performance evaluation of the model was conducted using confusion matrix with accuracy, precision, recall, and F1-Score values, which showed an average accuracy of up to 99.6% with increasing datasets. The real-time system test results show the success of detecting facial expressions even when faced with variations in environmental conditions. This system has the potential to be applied in various fields, such as human-machine interaction, security, and education, and can be improved by increasing the variety of expressions recognized and integrating expert systems for more complex emotion analysis.]]>
Copyrights © 2025
