Communications of the ACM
USC Researchers Develop State-of-the-Art Biometric Security Systems
Researchers at the University of Southern California's Information Sciences Institute have developed state-of-the-art biometric security systems for iris, face, and fingerprint recognition.
Credit: USC Viterbi School of Engineering
Researchers at the University of Southern California's Information Sciences Institute have developed state-of-the-art biometric security systems for iris, face, and fingerprint recognition, under the auspices of the Biometric Authentication with Timeless Learner project.
The system analyzes a biometric sample using multispectral data by shining light-emitting diode (LED) lights with different wavelengths on the sample. Machine learning algorithms analyze the collected data to differentiate between actual and spoofed biometrics.
Tests performed by the John Hopkins Applied Physics Laboratory showed that the fingerprint and iris recognition systems were respectively 99.08% and 99.36% accurate in detecting spoofs, while the facial recognition system was 100% accurate.
From USC Viterbi School of Engineering
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found