 |
Michigan State University, USAWebsite: http://biometrics.cse.msu.eduEmail: |
Anil Jain is a University Distinguished Professor in the Department of Computer Science at Michigan State University. His research interests are pattern recognition, computer vision, machine learning and biometric recognition. He received the King-Sun Fu Prize, Guggenheim, Humboldt, Fulbright, IEEE Computer Society Technical Achievement and IEEE Wallace-McDowell awards. He is a Fellow of ACM and IEEE and served as the Editor-in-Chief of the IEEE Trans. on Pattern Analysis and Machine Intelligence and a member of the IEEE Publications Board. He is the co-author of a number of books, including Handbook of Biometrics, Handbook of Multibiometrics, Handbook of Face Recognition, Handbook of Fingerprint Recognition and Algorithms for Clustering Data. He is a member of the National Academies panel on Information technology and previously served on its study teams on Whither Biometrics and Improvised Explosive Devices. He also served as a member of the Defense Science Board.
Next Generation Biometric Recognition Systems
Prevailing methods of person identification rely mainly on credentials (ID cards, driver license, PIN). However, these credentials are no longer meeting the growing threats of security breach and identity theft. As a result, a large number of government and commercial organizations worldwide are adopting biometric technology in critical applications like civil registry, international border crossing, government benefits programs, and access control. A biometric system recognizes a person based on her anatomical or behavioural characteristics. Unlike credentials, biometric traits (e.g., fingerprint, face, and iris) cannot be lost, stolen, and easily forged; they are also supposed to be persistent and unique. While biometric recognition, in particular, automatic fingerprint identification systems (AFIS), has been successfully used in law enforcement and forensics for over one hundred years, its adoption in many emerging large scale identity applications is posing new challenges and opportunities to pattern recognition and computer vision research communities. One such application is India’s Unique ID (UID) project, which is expected to identify a population of over one billion citizens. The design of a biometric system depends on the application requirements with respect to recognition accuracy, throughput, user acceptance, system security, and robustness to data quality. Next generation biometrics technology must offer solutions to high quality biometric data acquisition, robust representation and matching algorithms, interoperability, user privacy, system security, and information fusion. This talk will present our ongoing research on latent fingerprint matching, extended fingerprint features, facial aging, template protection, soft biometric attributes (scars, marks and tattoos), and heterogeneous face recognition in support of next generation biometric systems.