Biometric Recognition: How Do I Know Who You Are?

His research interests include statistical pattern recognition, computer vision and biometric authentication. Biometrics refers to the automatic identification (or verification) of an individual (or a claimed identity) by using certain physiological or behavioral traits associated with that person. By using biometrics, it is possible to establish an identity based on who you are, rather than by what you possess (e.g., an ID card) or what you remember (e.g., a password). Current biometric systems make use of fingerprints , hand geometry, iris, face, voiceprint and gait to establish a person's identity. While bio-metric systems have limitations, they are being deployed in a number of applications including computer logins, grocery stores, banks, Disney Parks and international border crossings (e.g., US-VISIT program). The successful implementation of these systems does not imply that biometrics is a solved problem. There is a significant room to improve the performance of these systems. We will present challenges in designing robust and secure bio-metric systems, state-of-the-art recognition performance and fusion strategies for multi-modal biometric system.