Facial Emotion Recognition using Stress Meter

Abstract

As the population increases in the world, the ratio of health cares is rapidly decreasing. Therefore, there is an urgent need to create new technologies to monitor the physical and mental health of people during their daily life. In case of stress recognition using a biological signal and thermal image, a device acquiring the corresponding information is required and an algorithm that recognize behavior of the person from images acquired with a general camera. The deep neural network that receives facial landmarks as input to take advantage of the fact that eye, mouth, and head movements are different from normal situations when a person is stressed.