Authors:
José Almeida
1
and
Fátima Rodrigues
2
Affiliations:
1
Polytechnic of Porto, School of Engineering, Rua Dr. António Bernardino de Almeida, Porto, Portugal
;
2
Interdisciplinary Studies Research Center (ISRC), Polytechnic of Porto, School of Engineering, Porto, Portugal
Keyword(s):
Stress Detection, Emotion, Facial Expression Classification, Convolutional Neural Networks.
Abstract:
Stress is the body's natural reaction to external and internal stimuli. Despite being something natural, prolonged exposure to stressors can contribute to serious health problems. These reactions are reflected not only physiologically, but also psychologically, translating into emotions and facial expressions. Based on this, we developed a proof of concept for a stress detector. With a convolutional neural network capable of classifying facial expressions, and an application that uses this model to classify real-time images of the user's face and thereby assess the presence of signs of stress. For the creation of the classification model was used transfer learning together with fine-tuning. In this way, we took advantage of the pre-trained networks VGG16, VGG19, and Inception-ResNet V2 to solve the problem at hand. For the transfer learning process two classifier architectures were considered. After several experiments, it was determined that VGG16, together with a classifier based o
n a convolutional layer, was the candidate with the best performance at classifying stressful emotions. The results obtained are very promising and the proposed stress-detection system is non-invasive, only requiring a webcam to monitor the user's facial expressions.
(More)