Facial Expression Detection is an important application of Artificial Intelligence and Computer Vision that enables machines to recognize human emotions from facial images. This project proposes a real-time facial expression detection system using the YOLOv8 deep learning model. YOLOv8 is chosen because of its high detection accuracy, fast processing speed, and ability to perform real-time object detection. The system first detects the human face from an image or live webcam feed and then classifies the facial expression into emotion categories such as happy, sad, angry, surprised, fearful, disgusted, or neutral. The dataset is preprocessed through image resizing, normalization, and data augmentation to improve the model's performance and robustness. During training, YOLOv8 learns important facial features and patterns that distinguish different emotions. After training, the model is evaluated using standard performance metrics such as accuracy, precision, recall, and F1-score. The developed system provides fast and reliable emotion recognition under different lighting conditions and facial orientations. This project demonstrates the effectiveness of YOLOv8 in building an efficient facial expression detection system for real-time applications. The proposed system can be used in healthcare, smart classrooms, driver monitoring, security surveillance, human-computer interaction, customer behavior analysis, and intelligent robotics. Overall, the project highlights the potential of deep learning and YOLOv8 to improve emotion recognition systems with greater speed, accuracy, and practical usability.

Soumya E, Sivaharini S D, Shamprasath R, Sabari S.K, Mrs. Rubadevi G,"YOLOv8-Based Facial Expression Detection and Classification Using Affection AffectNet Data" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(4): Page(484-491) July - August 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.