The Community for Technology Leaders
Green Image
Issue No. 03 - May/June (2011 vol. 13)
ISSN: 1521-9615
pp: 31-37
Dário Augusto Borges Oliveira , Pontifical Catholic University of Rio de Janeiro
Raul Queiroz Feitosa , Pontifical Catholic University of Rio de Janeiro
Antonio Carlos Censi , Montreal Informática
Raphael Pithan Brito , Montreal Informática
Álvaro de Lima Veiga-Filho , Pontifical Catholic University of Rio de Janeiro
José Luiz Buonomo de Pinho , Montreal Informática
ABSTRACT
<p>Texture-based automatic face recognition (AFR) methods find global similarities between two faces by computing their local regional similarities. A novel method based on Fisher discriminant analysis is proposed to estimate each region's contribution to the global similarity score. Experimental results show that the method considerably improves recognition performance for texture-based AFR.</p>
INDEX TERMS
Biometrics, face recognition, local binary pattern, local phase quantization, software, scientific computing
CITATION
Dário Augusto Borges Oliveira, Raul Queiroz Feitosa, Antonio Carlos Censi, Raphael Pithan Brito, Álvaro de Lima Veiga-Filho, José Luiz Buonomo de Pinho, "Weighting Estimation for Texture-Based Face Recognition Using the Fisher Discriminant", Computing in Science & Engineering, vol. 13, no. , pp. 31-37, May/June 2011, doi:10.1109/MCSE.2010.150
107 ms
(Ver 3.1 (10032016))