ABSTRACT
With the aim of identifying how facial recognition is used in monitoring
and attendance control systems, this study presents a systematic
literature review (SLR) on the topic. It was found that the
most employed Artificial Intelligence technique was Convolutional
Neural Networks (CNN). Regarding algorithmic approaches, the
Haar Cascade Classifier was used in most studies. Concerning the
datasets, proprietary databases were the most frequent. In terms of
the number of images in the datasets, the analyzed studies ranged
from small experimental sets to databases with millions of images,
and the employed hardware ranged from affordable devices to highperformance
GPUs. The test scenarios explored both controlled
environments, with variations in lighting and angles, and practical
applications in real-world settings. Finally, accuracy rates ranged
from 78.40% to 100%, with an average of 96.02%, while precision
rates varied between 80% and 100%, with an average of 94.98%.
The main contributions of this study lie in identifying the most
effective techniques, the challenges faced, and the gaps that may
guide future studies.