Published Paper Details:

This study introduces an emotion-driven music recommendation system that harnesses the power of facial expression detection to personalize user experiences. By utilizing a Convolutional Neural Network (CNN) for emotion recognition, the system captures facial features from webcam images to accurately identify emotional states such as happiness, sadness, anger, and surprise. Based on the detected mood, it curates a YouTube playlist that aligns with the user's emotions, enhancing their listening experience in real time. The system operates in two key stages: a training phase, where the model learns to recognize facial cues associated with various emotions, and a real-time detection phase, where the user's mood is continuously analyzed. By integrating deep learning and image processing techniques, the system ensures precise emotion recognition, enabling accurate music recommendations. This approach not only enhances personalization but also highlights the potential of AI-driven solutions in music recommendation systems. Future enhancements may include incorporating more advanced emotion detection algorithms, expanding the music library for greater cultural diversity, and improving adaptability to individual user preferences, further enriching the immersive experience.