Music Recommender System for Users Based on Emotion Detection through Facial Features

In recent years, facial emotion detection received massive attention because of its applications in computer vision and human-computer interaction fields. Due to the active works in this field, various algorithms and applications were proposed and implemented. In this research, we propose a recommender system for emotion recognition that is capable of detecting the user emotions and suggest a list of appropriate songs that can improve his mood. A brief search was conducted on how music can affect the user mood in short-term to gain knowledge and enable us to provide the users with a list of music tracks that work well on improving the user moods. The proposed system detects the emotions, if the subject has a negative emotion then specific playlist will be presented that contains the most suitable types of music that will improve his mood. On the other hand, if the detected emotion is positive, a suitable playlist will be provided which includes different types of music that will enhance the positive emotions. Implementation of the proposed recommender system is performed using Viola-Jonze algorithm and Principal Component Analysis (PCA) techniques, we were able to implement the proposed system successfully in MATLAB(R2018a).