Biometric Recognition: How Do I Know Who You Are?

Prof. Anil K. Jain, Michigan State University


Abstract

Should Alice be allowed to enter the country? Is Bob entitled to access the database? Has John been convicted before? Is Charlie the real owner of the credit card? Every day, a variety of organizations pose questions such as these about the identity of individuals. An emerging identification technology that is being increasingly adopted to identify individuals is biometric recognition - automatic person recognition based on anatomical or behavioral characteristics such as fingerprint, face, iris and voice. Biometrics allows us to confirm or establish a person's identity based on who he is, rather than by what he possesses (e.g., ID card) or what he remembers (e.g., password). It is, therefore, not surprising to see biometrics permeating our society (laptops, mobile phones, border crossings, national ID cards and even Disney parks). Biometrics is not a new idea. Pioneering work by Faulds, Galton and Henry over 100 years ago established that each print of a finger exhibits a unique pattern that persists over time. This set the stage for the development of automatic fingerprint identification systems (AFIS) that are now used by almost every law enforcement organization worldwide. The success of fingerprints in law enforcement coupled with growing concerns related to homeland security, financial fraud and identity theft has generated a renewed interest in biometrics. This talk will present an overview of biometric recognition, emerging applications and our ongoing research on (i) fingerprint and palmprint matching, (ii) fingerprint individuality, (iii) face recognition and (iv) matching and retrieval of scars, marks and tattoo (SMT) images.

Detailed information can also be found at:

http://viterbi.usc.edu/cgi-bin/cal_make.pl?p1=WOR200901291530163000.000.002


Maintained by Dian Gong