SONG RECOMMENDER SYSTEM

Music has an impact on human brain activity. Users can sustain a specific emotional state with the aid of an emotion-based music player with an automatic playlist. An emotion-based music player that builds playlists from user images is suggested by this study. This process has been automated using a variety of algorithms. Nevertheless, current algorithms are slow, need more hardware to operate, and are incredibly inaccurate. This paper presents an algorithm that not only automates the process of generating an audio playlist, but also to classify those songs which are newly added and the main task is tocapture current mood of person and to play song accordingly. This enhances the system’s efficiency, faster and automatic. The main goal is to reduce the overall computational time and the cost of the designed system. It also aims at increasing the accuracy of the system. The most important goal is to make change the mood of person if it isa negative one such as sad, depressed. This model is validated by testing the system against user dependent and user independent dataset.