Understanding emotions is one of the great abilities acquired by human beings,
as it allows the understanding of facial expressions that facilitate the capture of
important information about other individuals, which are used for the perception of
mental or emotional states. Advances in Artificial Intelligence (AI), more specifically in
Deep Learning with the advent of Artificial Neural Networks (ANN), have enabled
machines to infer human emotions through image analysis. Within this context, this
study proposes a Systematic Review of the Literature in order to explore the various
techniques and algorithms based on Artificial Intelligence for the recognition of
emotions by detecting facial expressions. The initiative is part of the WHOT (Women's
Health Observer Tool) 2.0 project, which proposes an optimization of the tool's
emotions inference module, whose purpose is to identify, through a combination of
facial expression recognition and interview with a digital questionnaire,
psychobehavioral patterns denoters of violence against women. The results suggest that
database uses with controlled images in the laboratory, combined with Convolutional
Neural Networks (CNN's) such as VVG and RESnet, have excellent performances in
their tests.
|
