FaceFetch: A User Emotion Driven Multimedia Content Recommendation System Based on Facial Expression Recognition

Recognition of facial expressions of users allows researchers to build context-aware applications that adapt according to the users' emotional states. Facial expression recognition is an active area of research in the computer vision community. In this paper, we present Face Fetch, a novel context-based multimedia content recommendation system that understands a user's current emotional state (happiness, sadness, fear, disgust, surprise and anger) through facial expression recognition and recommends multimedia content to the user. Our system can understand a user's emotional state through a desktop as well as a mobile user interface and pull multimedia content such as music, movies and other videos of interest to the user from the cloud with near real time performance.