DEEP LEARNING BASED PERSONALIZED MUSIC RECOMMENDATION SYSTEM^

Abstract

In day to day stressful environment, there is truancy for the appropriate relaxation time for all professionals. To make a person stress free many stress releasing methods are used and the work pressure and vexation of any kind of person can be recognized using their emotion. In this paper, the human face plays an important role in analyzing an individual’s mood through their facial expression. The objectives of the work are to identify the person and the emotion of the person with the help of their facial expression and play the song based on their expression. A facial expression is a discernible manifestation of the emotive state, cognitive activity, motive, and psychopathology of a person. Homo sapiens have been blessed with an ability to interpret and analyze an individual’s emotional state. However, machines were deprived of a complex brain like a human’s, which could recognize, distinguish, and perceive different emotions accurately. Ergo, an urge to craft sophisticated intelligent systems, equipped with such skills persisted. Here we applied various deep learning methods to identify the emotions of the person like happy, sad, anger, disgust, fear, surprise and neutral. The Kaggle Facial Expression Recognition challenge along with the FER2013 dataset is used to identify the facial expression.