Moodsync Based Music System using Emotion Detection

---

Abstract

Facial expression is one of the most effective ways for human being to express their emotions and intentions. The development of machine learning has created new opportunities to address real-world issues. Machine learning is the key technology for detecting facial expressions, requiring a variety of algorithms and real-time applications. In this paper, the Moodsync based adaptive music system is designed to provide a complete solution for people who want to reduce stress and encourage relaxation. It includes a song recommendation system and mood lighting feature. This novel method utilizes a curated Indian-origin playlist by using YouTube API. The proposed method utilizes facial recognition to determine the user's emotional state and make appropriate music recommendations. Using DeepFace and OpenCV, the user's facial expressions are recorded and analyzed to choose a song based on the current mood. The song beats are synchronized with the room's lighting to enhance the listening experience. The system obtained 93% accuracy, which is higher than previous methods.

---

Keywords

Machine learning, Emotion recognition, Music system, Youtube API, DeepFace with OpenCV.