BDBComp
Parceria:
SBC
MFISys - Um Sistema Biométrico Multimodal de Classificação De Imagens de Faces e Íris

Delorme, A. L.Adilson Gonzaga

This work describes a biometric authentication system based on the fusion of two user-friendlymodalities: Iris and Face. A single biometric system may not be sufficiently accurate for manyapplications. In this case, a Multimodal system can provide a more balanced solution to the securityand convenience requirements. The MFISys specifically apply 2-D discrete wavelet transform toextract the feature sets of low dimensionality from the iris and face. In order to obtain the final feature vector the results are concatenated. And then, Euclidian Distance operator is used to classify the images. The tests state that, in all cases, the multimodal system results in better classification.

http://www.lbd.dcc.ufmg.br/colecoes/wvc/2006/0039.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD