Desenvolvimento preliminar de um algoritmo de reconhecimento facial em tempo real através de redes neurais convolucionais

Diana Rocha, João Pereira, Maria Melo, Bruno C. Bispo, Pedro M. Rodrigues

Research output: Contribution to conferencePaper

18 Downloads

Abstract

This work presents the preliminary results of the development of a real-time facial recognition algorithm through convolutional neural networks (CNNs). Facial elements, namely, face, mouth, nose and eyes, are detected by the Viola-Jones algorithm. Each facial element is used to train a CNN. The training results show 100% identification accuracy. Real-time tests demonstrate a need for improvement. The image base will be expanded in the future to carry out a rigorous procedure for training and testing the algorithm.
Original languagePortuguese
Number of pages2
DOIs
Publication statusPublished - Nov 2020
EventXXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais - Florianópolis, Brazil
Duration: 22 Nov 202025 Nov 2020
https://biblioteca.sbrt.org.br/events/13

Conference

ConferenceXXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais
Country/TerritoryBrazil
CityFlorianópolis
Period22/11/2025/11/20
Internet address

Keywords

  • Face recognition
  • Real time
  • Convolutional neural network
  • Viola-Jones algorithm

Cite this