Music Recommendation System by Emotion for Multiple Faces

Facial emotion analysis plays a crucial role in enhancing human-computer interaction, entertainment systems, and personalized experiences. In this project, we propose a music recommendation system that detects emotions from multiple users' facial expressions and recommends suitable music based on the dominant emotion. Our system employs the YOLO model for real time, high-accuracy face detection, efficiently detecting multiple faces in a group setting. Once the faces are detected, the facial expressions are analyzed using a Convolutional Neural Network (CNN) model, trained to classify emotions into five categories: happy, sad, angry, surprised, and neutral. Based on the dominant emotion from the group of faces, the system recommends music from various genres to match or influence the emotional atmosphere. This framework provides a novel approach to personalized group-based music recommendation, ensuring both fast face detection and accurate emotion recognition. Index.