EmoMusic: a Facial Emotion-Based Music Recommendation System

Selecting music that matches an individual's emotional state requires significant effort and often yields inaccurate results. To overcome this challenge, this study proposes a real-time music recommendation system powered by facial emotion recognition. The system utilizes a webcam to capture and analyze facial expressions, identifying emotions such as happiness, sadness, anger, or neutrality. Machine learning algorithms ensure precise emotion detection, while integration with the YouTube API provides curated music recommendations that dynamically align with the user's mood. Optimized for real-time performance, the system seamlessly integrates advancements in computer vision, real-time video processing, and intelligent music retrieval. By automating the music selection process, this solution enhances user convenience, minimizes effort, and delivers a personalized music experience tailored to emotional needs. The core technologies driving this system include TensorFlow for model training, OpenCV for video processing, Streamlit for the user interface, and Deep Face in conjunction with the YouTube API for music recommendations.