EmotiTEA: A visual monitoring module based on the recognition of facial emotions with CNN

Oliveira I.; Silva J.L.; Quispe F.P.; Alvarez A.B. · Proceedings of the 2021 IEEE Engineering International Research Conference, EIRCON 2021 (2021) · DOI: 10.1109/eircon52903.2021.9613399

Resumen

The recognition of human facial emotions is a highly complex task and an open problem. This paper presents the EmotiTEA module that performs the recognition of facial emotions to be used in monitoring in real time. Two simple custom Convolutional Neural Networks (CNN) are studied, which were included in the module for specific tests. The results obtained under the test conditions indicate a satisfactory performance with the implemented CNNs and a promising behavior of the EmotiTEA module for the real time monitoring task.

Instituciones: Universidad Nacional de San Antonio Abad del Cusco