Open AccessANÁLISE DE MÉTODOS DE DETECÇÃO E RECONHECIMENTO DE FACES UTILIZANDO VISÃO COMPUTACIONAL E ALGORITMOS DE APRENDIZADO DE MÁQUINA
Author(s) -
Lucas José da Costa,
Thiago Luz de Sousa,
Francisco Assis da Silva,
Leandro Luiz de Almeida,
Danillo Roberto Pereira,
Almir Olivette Artero,
Marco Antônio Piteri
Publication year - 2021
Publication title -
colloquium exactarum
Language(s) - English
Resource type - Journals
ISSN - 2178-8332
DOI - 10.5747/ce.2021.v13.n2.e354
Subject(s) - computer science , eigenface , facial recognition system , haar like features , artificial intelligence , pattern recognition (psychology) , face detection , face (sociological concept) , social science , sociology
The advancement in technology in recent decades has provided many facilities for humanity in various applications, and facial recognition technology is one of them. There are several problemsto be solved to perform face recognition from digital images, such as varying ambient lighting, changing the face physical characteristics and resolution of the images used. This work aimed to perform a comparative analysis between some of thedetection and facial recognition methods, as well as their execution time. We use the Eigenface, Fisherface and LBPH facial recognition algorithms in conjunction with the Haar Cascade facedetection algorithm, all from the OpenCV library. We also explored the use of CNN neural network for facial recognition in conjunction with the HOG facial detection algorithm, these from the Dlib library. The work aimed, besides analyzing the algorithms in relation to hit rates, factors such as reliability and execution time were also considered