University of Calgary Researchers Advance Biometric Security
The University of Calgary’s Biometric Technologies Laboratory has developed a technology that will allow security systems for merging biometric data such as facial scans, fingerprints, and even the shape of the face, to come up with a learning system that acts like the human mind to make decisions.
By comparing and studying different biometric patterns to make a decision, the system is more accurate and the recognition process is greatly improved. PhysOrg reports that the technology is still algorithm-based but it can learn new patterns along the way. For example, when an error occurs due to a bad sample, the system can instead switch to behavioral patterns or facial recognition to verify a person’s identity.
“Our goal is to improve accuracy and as a result improve the recognition process,” says Gavrilova, a professor in the Faculty of Science. “We looked at it not just as a mathematical algorithm, but as an intelligent decision making process and the way a person will make a decision.”
The algorithm learns new biometric patterns and associates information from different data sets, allowing combined information, such as fingerprint, voice, gait or facial features, instead of relying on a single set of measurements.
Biometric information is becoming more available and common nowadays. It is no longer unusual to find one or two sets of biometric data being implanted on drivers’ licenses, passports and other forms of identification. The new security system being developed can interpret biometric data taken from different databases and use that to formulate an intelligent decision.
When it comes to security measures and needs, an advanced system which is able to think on its own and make judgment calls, becomes flexible especially in environments that frequently undergo a lot of changes. The advanced security system will also be able to train itself to highlight important features and then store these for future use.