Real Time Smart Music Player Using Facial Expression

Abstract

According to the World Happiness Report 2021, created by the World Happiness Council, it has ranked 140 countries based on how satisfied their citizens are. Due to COVID-19 pandemic, they observed there was large decline in mental health because of unemployment and decrease inperson gatherings resulting in a decrease in the happiness index of countries. Therefore, in this work we targeted to improve the emotional state of the person and make him happy, by recognizing the persons emotion and plays corresponding music will help user in changing their mood. Music's magical power has been scientifically established and people enjoy listening to music that reflects their emotional feelings, it is a stress-relieving tool and has the ability to control a wide range of psychological states. We used Viola Jones algorithm, Data augmentation and CoAtNet algorithm to detect the emotion of a person. A high accuracy is achieved with proposed CoAtNet model when compared to other methods like Conventional CNN, Principal Component Analysis (PCA) and SVM etc. We have also deployed the model on the STM32H747I Board.