International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 03 | Mar 2025
p-ISSN: 2395-0072
www.irjet.net
" SMART MUSIC PLAYER INTEGRATING FACIAL EMOTION RECOGNITION AND MUSIC MOOD RECOMMENDATION" Archi Jadhav1, Nanumaya Khatri2, Kalyani Naik3, Prajkta Ugale4, Prof Deepali Joshi5 1,2,3,4 B.E. Students Department of Computer Engineering
5 HOD, Department of Computer Engineering, Bharat College of Engineering, Opp. Gajanan Maharaj Temple,
Kanhor Road, Badlapur (West), Thane, Maharashtra - 421503 ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Emotion-based music recommendation is a
playlists, or genre-based sorting, which fail to capture a user's real-time emotional state. Listeners often find themselves searching for music that resonates with their current mood, which can be time-consuming and inefficient. Additionally, existing recommendation systems do not incorporate realtime facial emotion recognition to dynamically adjust music based on how a person feels at the moment. The lack of intelligent emotion-driven automation in music selection limits the overall user experience, making it difficult to achieve a truly immersive and personalized listening journey. This project addresses this gap by developing a real-time facial emotion-based music recommendation system, ensuring that users can effortlessly listen to music that aligns with their emotions.
growing field that aims to enhance user experience by suggesting songs that align with their emotional state. This paper presents an intelligent system that utilizes deep learning and computer vision techniques to detect human emotions and recommend music accordingly. The system leverages MediaPipe Holistic for facial and hand landmark extraction, and a pre-trained deep learning model to classify emotions. The detected emotion is then used to curate song recommendations in the user’s preferred language and platform, such as YouTube, Spotify, Apple Music, and more. The application is implemented using Streamlit for an interactive user interface, integrating a real-time camera feed for continuous emotion analysis. To ensure usability, the system provides a simple yet effective approach to emotion detection and music retrieval. The proposed solution aims to bridge the gap between mood recognition and music preferences, offering a personalized and immersive music experience Key Words: Emotions, Recommendation, Songs
CNN,
Detection,
1.2 OBJECTIVE The primary objective of this project is to develop a system that can automatically recognize facial expressions and recommend music based on the detected emotions. The system aims to enhance user experience by eliminating the need for manual song selection and providing a more intuitive approach to music discovery. By integrating facial emotion recognition with a music mood classification system, the project seeks to bridge the gap between human emotions and digital music platforms. Another key goal is to create a seamless and user-friendly interface where individuals can not only receive music recommendations but also refine the system’s suggestions based on their personal preferences.
Music
1.INTRODUCTION Music has long been recognized as a powerful medium for influencing human emotions. With the advancement of artificial intelligence and machine learning, it is now possible to create personalized music recommendations that adapt to a listener’s emotional state in real time. The Smart Music Player Integrating Facial Emotion Recognition and Music Mood Recommendation is an innovative system designed to enhance the listening experience by automatically detecting a user’s emotion through facial expressions and recommending songs that match their mood. By utilizing computer vision through Mediapipe and a deep learning model for emotion classification, the system identifies facial expressions and maps them to a corresponding mood-based music playlist. This eliminates the need for manual song selection and provides a seamless, emotionally adaptive music experience.
1.3 SCOPE The scope of this project extends to various domains, including artificial intelligence, human-computer interaction, and personalized entertainment. By integrating deep learning models, Mediapipe for facial landmark detection, and real-time emotion recognition, this system is capable of adapting music recommendations dynamically. Users can select their preferred music platform (YouTube, Spotify, Apple Music, etc.), language, and singer preferences to further refine their experience. In the future, this system could be enhanced with voice-based emotion detection, EEGbased mood tracking, or even integration with smart assistants for a fully automated experience. Additionally, this technology has the potential to be used in therapy, wellness
1.1 PROBLEM DEFINATION Traditional music streaming platforms rely on static recommendations based on past listening history, predefined
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 741