|Communications on Applied Electronics|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 3 - Number 4|
|Year of Publication: 2015|
|Authors: Benson-Emenike Mercy E., Nwachukwu E.O.|
Benson-Emenike Mercy E., Nwachukwu E.O. . An Improved Intelligent Multi Biometric Authentication System. Communications on Applied Electronics. 3, 4 ( November 2015), 27-38. DOI=10.5120/cae2015651930
The beginning of the 21st century was marked with events that focused on the world’s attention to public security. Increase in technological advancement gave people possibilities of information transfer and ease of physical mobility unseen before. With those possibilities comes risk of fraud, theft of personal data, or even theft of identity. One of the ways to prevent this is through biometric authentication system. Unibiometric systems rely on the evidence of a single source of information whereas multibiometric systems consolidate multiple sources of biometric evidences. Multibiometric systems, if designed properly, are able to enhance the matching performance. In this paper, Intelligent Multi-Biometric Authentication System, face and fingerprint biometric traits are used. When the images are captured, preprocessing in face and fingerprint images is done using Enhanced Extracted Face (EEF) method and Plainarized Region Of Interest (PROI) method respectively. These are fed into a Cascaded Link Feed Forward Neural Network(CLFFNN) which is a classifier trained with back-propagation algorithm. CLFFNN comprises of CLFFNN(1) used for training and CLFFNN(2) used as the main classifier. They are arranged in cascades. Afterwards, both outputs from face and fingerprints are combined using AND operation.