Copyright © 2026 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{200077,
        author = {indrajeet patel and Nihal singh and Ayush Kumar singh and Akhilesh Kumar and Harshit jaiswal and Puneeta Singh},
        title = {Emotion Based Music Recommendation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {874-879},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200077},
        abstract = {The integration of artificial intelligence with multimedia systems has opened new avenues for developing intelligent and emotionally aware applications. This project focuses on building an emotion-based music recommendation system using deep convolutional neural networks, specifically leveraging the VGG19 architecture.
The application processes user facial expressions using a trained TensorFlow model and maps them to predefined emotional categories such as angry, happy, fearful, disgusted, sad, neutral, and surprised. Each detected emotion is linked to a curated playlist inside an Android application built using Android Studio. The system uses TensorFlow Lite for on-device AI inference, enabling real-time, offline, optimized performance. This report presents an extensive overview of dataset preprocessing, normalization, augmentation, model training, optimization, Android deployment, testing, and performance benchmarking. This document provides an in-depth technical, theoretical, and practical understanding of system development.},
        keywords = {Emotion Recognition, Music Recommendation System, Convolutional Neural Network, VGG19, FER2013, TensorFlow Lite, Android Application},
        month = {May},
        }