Unveiling Stress through Facial Expressions: A Literature Review on Detection Methods

Abstract

Stress detection is crucial in various fields, including
healthcare, human-computer interaction, and automotive safety.
This paper presents a comprehensive comparison study of three
emotion detection modules: facial expression analysis, eyeblink
count, and eyebrow movements. The aim is to assess their effectiveness in detecting stress accurately. Each models is evaluated
based on its ability to discern stress levels in real-time scenarios.
By analyzing the data collected from different research papers
related to stress-inducing stimuli, we provide insights into the
strengths and limitations of each model. Additionally, we propose
a novel framework that integrates these modules to enhance stress
detection accuracy. The results indicate promising performance,
with the integrated framework demonstrating superior stress
detection capabilities compared to individual modules. This
research contributes to advancing stress detection methodologies,
paving the way for more reliable and efficient stress management
systems.