Communications of the ACM
Researchers Advance Biometric Security
University of Calgary professor Marina Gavrilova
Credit: Riley Brandt
A biometric security system developed by researchers at the University of Calgary can simulate the way the brain makes decisions about information from different sources.
Professor Marina Gavrilova, head of the university's Biometric Technologies Laboratory, describes the system as a kind of artificial intelligence application that can train itself to learn the most important aspects of new data and incorporate it into the decision-making process.
The system is designed to combine measurements from multiple biometric sources, such as fingerprint, voice, gait, or facial features. The system also prioritizes the information by identifying more important or prevalent features to learn, and adapts the decision-making to changing conditions, such as bad quality data samples, sensor errors, or an absence of one of the biometrics.
"The neural network allows a system to combine features from different biometrics in one, learn them to make the optimal decision about the most important features, and adapt to a different environment where the set of features changes," Gavrilova says. "This is a different, more flexible approach."
The goal of the project is to improve accuracy, which would boost the recognition process, Gavrilova notes.
From University of Calgary
View Full Article
Abstracts Copyright © 2012 Information Inc. 
, Bethesda, Maryland, USA
No entries found