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.

Related Posts

Article Topics

 |   |   |   |   |   |   |   | 

Latest Biometrics News


Leave a Reply

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

The ID16.9 Podcast

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics