Abstract

We propose an innovative system for automatically playing music based on facial emotion recognition. Traditional methods require manual selection, wearable devices, or audio feature-based classification. Our approach leverages convolutional neural networks (CNN) for detecting emotions from facial expressions, while Pygame & Tkinter generate music playlists. The system is tested on the FER2013 dataset, capturing facial expressions using an inbuilt camera and classifying emotions such as happy, angry, sad, surprise, and neutral. By reducing computational time and improving accuracy, this method enhances the efficiency of emotion-based music recommendations.