Anil Jain, University Distinguished Professor of computer and electrical engineering

Phone: (517) 355-9282
E-mail: jain@cse.msu.edu
Profile: www.cse.msu.edu/~jain/
Photo: hi-res jpg

Presentation: “Strengthening the Scientific Basis of Biometric Identification and Authentication – Biometrics: Applications, Challenges and Opportunities?”

Abstract: A wide variety of systems require reliable personal recognition schemes to either confirm or determine the identity of an individual requesting access to their services. The purpose of such schemes is to ensure that only a legitimate user, and not anyone else, accesses the rendered services. Examples of such applications include secure access to buildings, computer systems, cellular phones, e-commerce and international border crossings. Biometric recognition, or simply biometrics, refers to the automatic recognition of individuals based on their anatomical and behavioral characteristics. Biometrics makes it possible to confirm or establish an individual's identity based on who she is (e.g., fingerprints, voice, iris), rather than by what she possesses (e.g., an ID card) or what she remembers (e.g., a password). Biometric systems also introduce an aspect of user convenience; they alleviate the need for a user to remember multiple passwords associated with different applications. In spite of the fact that several large-scale biometric systems have been deployed (e.g., US-VISIT), design, implementation and performance evaluation of a biometric system are extremely challenging problems. Further, neither the inherent discriminative ability (i.e., the individuality) of a particular biometric trait nor the true performance of the deployed biometric systems is known. A biometric system must be robust to non-universality of the trait, noisy sensed data, large intra-class variability, and spoof attacks. This requires that we investigate following topics: invariant representation of biometric traits, measures of image quality, image enhancement algorithms, biometric data fusion, sample size requirement for evaluating system performance, liveness testing, social acceptance and cost-benefit analysis. As biometric systems are being increasingly deployed and standard biometric datasets are becoming available, this has opened up huge opportunities for researchers in several disciplines to address these challenging problems in biometrics recognition.

[ Back to Index ]