Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182228,
        author = {Harshini Kotgirwar and Sayali Thak},
        title = {Face Recognition Music Recommendation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {1253-1256},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182228},
        abstract = {We present an innovative approach for music playback that leverages facial expression recognition to deliver a more natural listening experience. Unlike conventional methods that rely on manual selection, wearable devices, or sound-based classification, our system streamlines the process by automating music organization and playback.
Our method utilizes a Convolutional Neural Network (CNN) for emotion detection, with Pygame and Tkinter incorporated to manage music recommendations efficiently. This design minimizes computational overhead and system costs, enhancing overall accuracy and performance. The system has been evaluated using the FER2013 dataset, with facial expressions captured via an inbuilt camera. Facial features are extracted from these images to identify emotions such as happiness, anger, sadness, surprise, and neutrality. Based on the detected emotion, a suitable music playlist is automatically generated.
The system’s architecture comprises three main components: a facial emotion recognition module, a music database, and a recommendation engine. The recognition module employs OpenCV in combination with deep learning frameworks like TensorFlow or PyTorch for precise emotion classification. By training the model with datasets such as FER-2013 and CK+, the system achieves high accuracy in detecting user emotions. The recommendation engine integrates content-based filtering with collaborative filtering to deliver personalized music suggestions. Additionally, the music database is structured according to emotional tones, ensuring a smooth connection between detected emotions and corresponding music recommendations.
This solution offers improved computational efficiency and faster response times compared to existing approaches, enhancing both system performance and user satisfaction.},
        keywords = {Facial Recognition, Feature Extraction, Emotion Recognition, Music Recommendation, Convolutional Neural Network (CNN), Pygame, Tkinter, Music Player, Camera.},
        month = {July},
        }