%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.23.23.50
%2 sid.inpe.br/sibgrapi/2015/07.23.23.50.04
%T Reconhecimento Facial 2D para Autenticação Contínua
%D 2015
%A da Silva, Adeilson Antônio,
%A Pamplona Segundo, Maurício,
%@affiliation Intelligent Vision Research Lab, Departamento de Ciência da Computação, Universidade Federal da Bahia, Brasil
%@affiliation Intelligent Vision Research Lab, Departamento de Ciência da Computação, Universidade Federal da Bahia, Brasil
%E Vieira, Thales Miranda de Almeida,
%E Mello, Vinicius Moreira,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K face recognition, continuous authentication, biometrics, computer vision.
%X This paper presents a continuous 2D face authentication system with the purpose of forbid unauthorized people to access an application. The use of 2D images makes the system more accessible, given the ease of finding cameras of this type in current computers. Because of the limiting factors on the use of 2D images, like pose variation and face occlusion, a normalization process is used to reduce the effects of those problems. With the score given by the recognition stage, the probability of the system being safe is calculated. The system was evaluated through 10 minutes long videos with variations in facial expression, pose and occlusion, and a equal error rate of approximately 8% was achieved.
%@language pt
%3 AdeilsonSilva-MauricioPamplona_Reconhecimento Facial 2D para Autenticação Contínua_Camera Ready.pdf