Design of a facial emotion recognition system using Deep Learning techniques

Ignacio Ramos. (2019). Design of a facial emotion recognition system using Deep Learning techniques. Final Career Project (TFM). Universidad Politécnica de Madrid, ETSI Telecomunicación.

Abstract:
This project is within the researching line of ‘NLP and Sentiment Analysis’ of the Intelligent System group of the ETSIT-UPM. The main objective is to design and develop a system capable of recognizing emotions from facial expressions. The project is divided into three phases: • Design and development of a facial emotion recognition system using Deep Learning techniques. To do so, various models are designed with different architectures, so that a comparison can be done in order to select the one with the best performance. • Design and development of a local app in order to test the model previously trained in a practical way. this app gathers information from the webcam in real-time and performs computer vision techniques in order to detect different faces presented in each frame of the video. Once the face has been isolated from the rest of the image, a preprocessing is done and then the model is used to recognize the emotion. • Implementation of a cloud-deployable app to detect emotions in real-time. As before, this app also gathers information served by the webcam, but with the aim of being deployed on the cloud, since it has been developed using NodeJS, a language widely used in web projects.