FB pixel

Biometrics experts discuss voice and face potential, presentation attacks at Israeli Winter School

Categories Biometric R&D  |  Biometrics News  |  Trade Notes
Biometrics experts discuss voice and face potential, presentation attacks at Israeli Winter School
 

The Identity and Biometric Applications Unit of Israel’s National Cyber Directorate partnered with the University of Haifa to hold a three-day “Winter School” on biometric identification, voice and face recognition.

Leading researchers, academics and industry stakeholders from around the world gathered in Israel for the first event of its kind, which was hosted by the University’s Center for Cyber Law and Policy and The Identity and Biometric Applications Unit of the National Cyber Directorate as a joint initiative.

In the event’s opening lecture, Professor Anil K. Jain of Michigan State University noted that “biometric identification strengthens medical records and medical documentation and enables better and more precise medical care, especially in developing nations.”

He also expressed optimism that the establishment of Israel’s National Biometric Laboratory will enhance biometric system performance testing and verification.

Professor Arun Ross of Michigan State University’s Department of Computer Science and Engineering discussed iris recognition and the importance of using near infra-red imaging to carry out biometric recognition capable of distinguishing even between otherwise identical twins.

Professor Rita Singh of Carnegie Mellon University discussed voice recognition, and the potential to create 3D facial images of an individual based on his or her voice.

IDIAP Research Center Senior Researcher Dr. Sebastien Marcel gave a presentation on presentation attacks against biometric systems, and the increasingly sophisticated methods of deception attackers use.

The third day focused on facial recognition, with Tel Aviv University Professor Galit Yovel comparing how humans and algorithms handle the same task. The shape of an individual’s lips and eyebrows, eye color, skin color and hair are the five main features influencing face recognition.

“When you change these features on a person, not only it makes it difficult for a human to identify that this is the same person, it also affects the performance of the advanced AI algorithms,” Yovel explains.

National Institute of Standards and Technology (NIST) Dr. Jonathon Phillips talked about the role of human examiners in complex biometric systems, based on his research on the performance of face recognition systems and human examiners compared to the ability of AI algorithms. The time is coming when AI algorithms will outperform human abilities, Phillips says.

Article Topics

 |   |   |   |   |   |   |   | 

Latest Biometrics News

 

What to do if certificates for passive authentication fail

By Ihar Kliashchou, Chief Technology Officer at Regula Electronic documents are praised for their top-notch security, mainly due to RFID chip…

 

Biometric passports get refresh in Indonesia, face hurdles in Lebanon and Kenya

Nations across the global south are looking to biometric passports as the next generation of travel documents. Indonesia will mark…

 

Biometrics, electronic devices and identity credentials converging

Biometrics in electronic devices and ID documents to support digital identity are a major theme of the week’s top stories…

 

SITA wraps up acquisition of Materna IPS

SITA reports it has completed all necessary regulatory and legal procedures and finalized its acquisition of Materna IPS, a provider…

 

Payface lands new retail biometric payments deal in Brazil

Brazilian face biometrics payments startup Payface has clinched a deal with supermarket chain Ítalo. Ítalo Supermercados, based in the southern…

 

EU to fund digital programs with €108m, including digital identity

The European Union has issued a new call for funding within the Digital Europe Programme (DIGITAL), allocating over 108 million…

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 Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events