2008 | OriginalPaper | Buchkapitel
A Robust Authentication System Using Multiple Biometrics
verfasst von : Md. Maruf Monwar, Marina Gavrilova
Erschienen in: Computer and Information Science
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this work, a multibiometric system has been developed to overcome the drawbacks associated with monomodal biometric systems, such as noise, intra-class variability, distinctiveness, non-universality and spoof attacks. Information from three different Fisher’s Linear Discriminant driven monomodal experts based on face, ear and signature biometric traits are combined through decision level fusion method. AND/OR, majority voting, weighted majority voting and behavioural knowledge space approaches of decision level fusion method are examined to achieve a higher recognition accuracy. Experimental results indicate that fusing information from multiple biometric traits can results in higher recognition rates. The system can be a contribution to homeland security or other intelligence departments.