MOOD BASED MUSIC RECOMMENDATION SYSTEM
Unknown authors
Abstract
A lot of research is being conducted in the field of Computer Vision and Machine Learning (ML), where machines are trained to identify various human emotions or moods.Machine Learning provides various techniques through which human emotions can be detected.One such method is neural network which detects emotions through facial expressions.In this paper "Mood-based music recommendation system proposed", this system is web-based application which does real time mood detection and displays a list of songs as per the mood of the user on the YouTube page.The system uses neural networks and libraries such as OpenCV, Kera's, and Media pipe for facial detection.In addition to this system also provide an option of using "emojis" to the user in case of the user is not comfortable using his/her camera.The proposed system was tested on a dataset of facial expressions achieved an accuracy of approximately 86.57% and recommend top songs based on threshold values for each mood.This system provides a personalized and immersive music experience that can enhance user engagement and enjoyment.