Home > Seminars > Is that eye alive or dead? Current reliability challenges in iris recognition

Is that eye alive or dead? Current reliability challenges in iris recognition

Start:

5/3/2018 at 3:30PM

End:

5/3/2018 at 4:45PM

Location:

356A Fitzpatrick

Host:

College of Engineering close button
headerbottom

Ronald Metoyer

Ronald Metoyer

VIEW FULL PROFILE Email: rmetoyer@nd.edu
Phone: 574-631-5893
Website: http://www.nd.edu/~rmetoyer/
Office: 325C Cushing

Affiliations

College of Engineering Assistant Dean of Diversity and Special Initiatives
Dr. Metoyer's research interests are broadly in the areas of human-computer interaction with an emphasis on information visualization and applications in the areas of health and wellness, education, intelligence analysis, and software engineering.
Click for more information about Ronald
574-631-5893
Add to calendar:
iCal vCal

Iris recognition has more than two decades of history. Despite many successful large-scale implementations, and current efforts towards including iris recognition as the third mode in biometric passports, some of its reliability aspects are debated, and some of its potentials are not yet fully explored.

In this lecture I will present my recent research results related to making iris recognition more reliable. I will discuss biologically-driven short-term and long-term stationarity of iris recognition, including iris template aging, influence of eye conditions on the identification performance, and an emerging possibility of using iris after death to recognize decedents. The discovery that iris can serve as a biometric identifier even three weeks after demise brings new security concerns, but also opens new possibilities for forensic analysis, and calls for new computer vision methods accounting for post-mortem changes observed in the eye. An important part of the lecture will be dedicated to presentation attacks and the methods using static and dynamic properties of the eye to detect if the object presented to the sensor is an authentic and alive iris. I will also discuss recent experiments conducted here at Notre Dame related to human interaction with the iris recognition system, and I will show that observing how humans recognize iris images helps in building more accurate iris matching algorithms.

Seminar Speaker:

Dr. Adam Czajka

Dr. Adam Czajka

Research Assistant Professor, University of Notre Dame

Adam Czajka received his M.Sc. in Computer Control Systems, and his Ph.D. in Biometrics from Warsaw University of Technology (WUT, Poland) in 2000 and 2005, respectively (both with the highest honors).

Dr. Czajka is currently a Research Assistant Professor in the Department of Computer Science and Engineering here at the University of Notre Dame, and an Assistant Professor with the Research and Academic Computer Network – national research institute (NASK) in Poland. He is also the Chair of the Polish Standardization Committee on Biometrics, a Senior Member of the Institute of Electrical and Electronics Engineers, Inc. (IEEE), and an active member of the European Association for Biometrics. He is a member of the IET Biometrics editorial board and serves as the Associate Editor in IEEE Access.

Before coming to Notre Dame, Dr. Czajka was the Chair of the Biometrics and Machine Learning Laboratory at the Institute of Control and Computation Engineering at WUT, the Head of the Postgraduate Studies on Security and Biometrics, the Vice Chair of the NASK Biometrics Laboratory, and a member of the NASK Research Council.

Scientific interests of Dr. Czajka include biometrics and security, computer vision, and machine learning.