FB pixel

Researchers develop anti-spoofing techniques for iris biometric recognition

New technique based on sparse representation coding
Researchers develop anti-spoofing techniques for iris biometric recognition

New joint research between Notre Dame’s College of Engineering and Universidad Católica de Chile (PUC-Chile) has explored the potential and susceptibility to presentation attacks of iris recognition biometrics.

Sponsored by the Luksic Family Collaboration Grant, the new collaboration focused on helping iris recognition systems detect those attacks that utilize unknown objects such as printouts of false irises or cosmetic contact lenses.

“It’s a very Hollywood-ish thing, but my team has demonstrated in the past that dead eyes can be used for recognition even a few weeks post-mortem, so developing appropriate countermeasures is a must,” explained Adam Czajka, assistant professor at Notre Dame’s Department of Computer Science and Engineering.

As part of the joint research, Czajka collaborated with Domingo Mery, full professor in the Department of Computer Science at PUC-Chile, to use sparse representation coding to offer compact and representative feature sets for various visual recognition tasks.

Using this approach, the scientists managed to program an algorithm that can effectively adapt to unknown false iris images.

“Thanks to [Czajka’s] graduate student Aidan Boyd, who improved and adapted an algorithm initially developed for face recognition, we have obtained very good results in iris recognition that are about to be published,” Mery said.

Looking forward, the scientists said they will continue their collaboration to improve the anti-spoofing capabilities of their iris recognition algorithms further.

Related Posts

Article Topics

 |   |   |   |   | 

Latest Biometrics News

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics