Biometric Recognition: Techniques, Applications and Challenges

Anil K. Jain

University Distinguished Professor,

Department of Computer Science and Engineering,

Michigan State University.

3115 Engineering Building,

East Lansing, MI 48824. Ph: 517-355-9282, Fax: 517-432-1061



Arun Ross

Assistant Professor,

Department of Computer Science and Electrical Engineering,

West Virginia University.

PO Box 6109,

Morgantown, WV 26506. Ph: 304-293-0405, Fax: 304-293-8602




Traditionally, passwords (knowledge-based security) and ID cards (token-based security) have been used to moderate access to restricted systems.  However, security can be easily breached in these systems when a password is divulged to an unauthorized user or a card is stolen by an impostor. Furthermore, simple passwords are easy to guess (by an impostor) and difficult passwords may be hard to recall (by a legitimate user). The emergence of biometrics has addressed the problems that plague traditional verification methods. Biometrics refers to the automatic identification (or verification) of an individual (or a claimed identity) by using certain physiological or behavioral traits associated with the 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, retina, face, facial thermograms, signature, gait, palmprint and voiceprint to establish a person¡¯s identity. While biometric systems have their limitations they have an edge over traditional security methods in that they cannot be easily stolen or shared. Besides bolstering security, biometric systems also enhance user convenience by alleviating the need to design and remember passwords.

This tutorial is intended to provide an introduction to the field of biometric recognition.  A biometric system will be viewed as a pattern recognition system consisting of three main modules: the sensor module, the feature extraction module and the feature matching module. The design of such a system will be studied in the context of 4 commonly used biometric modalities - fingerprint, face, hand, and iris. Various algorithms that have been developed for each of these modalities will be presented. We will discuss techniques to evaluate the recognition performance of a biometric system. Methods to safeguard the biometric templates of enrolled users will also be presented. Finally, we will discuss some of the challenging issues that biometric systems have to contend with in a real-world environment and the methods used to address these challenges.

The tutorial will target graduate students, researchers and technical personnel who are interested in understanding the details involved in designing a biometric system. A basic background in image processing and statistics will be useful.



(1) What is Biometrics?

  • Definition and an example

  • Historical background and usage in forensics (e.g., Bertillon system, Henry/Galton system)

(2) Biometric Traits

  • Description of commonly used traits

  • Physical versus behavioral traits

  • Advantages/drawbacks of various biometric traits

(3) Biometric Applications

  • Real world applications using popular traits

  • Emerging applications

  • Challenges

(4) Designing a Biometric System

  • Biometrics as a pattern recognition system

  • Enrolment, verification, identification, watch list

  • Generating templates

  • Intra-class variation and inter-class similarity

(5) Performance evaluation

  • Failure to enroll (FTE), Failure to Acquire (FTA)


  • ROC curves, DET curves

  • FVC2002, FRVT2002, NIST2000

  • Public domain databases

  • Best practices

(6) Securing Biometric Templates

  • Privacy concerns

  • Function creep

  • Identity creep

  • Cancellable biometrics

  • Watermarking templates

(7) Case Studies: description of commonly used biometric representation and matching schemes, including

  • Fingerprint

  • Face

  • Hand (geometry + palm)

  • Iris

(8) Multibiometrics

  • Advantages

  • Strategies

  • Performance gain

(8) Existing standards

  • BioAPI

  • M1 (USA)

(9) Challenges in Biometrics

  • Scalability issues

  • Template aging

  • Interoperability

(10) Summary and Conclusions



Anil K. Jain is a University Distinguished Professor in the Department of Computer Science and Engineering at Michigan State University. He was the Department Chair between 1995 and 1999. His research interests include statistical pattern recognition, exploratory pattern analysis, Markov random fields, texture analysis, 3D object recognition, medical image analysis, document image analysis and biometric authentication. Several of his papers have been reprinted in edited volumes on image processing and pattern recognition. He received the best paper awards in 1987 and 1991, and received certificates for outstanding contributions in 1976, 1979, 1992, 1997 and 1998 from the Pattern Recognition Society. He also received the 1996 IEEE Transactions on Neural Networks Outstanding Paper Award. He is a fellow of the IEEE and International Association of Pattern Recognition (IAPR). He has received a Fulbright Research Award, a Guggenheim fellowship and the Alexander von Humboldt Research Award. He delivered the 2002 Pierre Devijver lecture sponsored by the International Association of Pattern Recognition (IAPR). He holds six patents in the area of fingerprint matching.

Arun Ross is an Assistant Professor in the Lane Department of Computer Science and Engineering at West Virginia University. He obtained his Ph.D. in Computer Science and Engineering from Michigan State University in 2003. His Ph.D. dissertation was on the topic of biometric fusion in the context of fingerprint recognition. Between July 1996 and December 1997, Ross worked with the Design and Development group of Tata Elxsi (India) Ltd., Bangalore. He also spent three summers (2000 - 2002) with the Imaging and Visualization group at Siemens Corporate Research (SCR), Inc., Princeton, working on fingerprint recognition algorithms. Ross¡¯ current research activities include multimodal biometrics, fingerprint indexing, face modeling and multi-spectral iris analysis. He is actively involved in the development of Pattern Recognition and Biometrics curricula at West Virginia University. His research interests include pattern recognition, classifier combination, machine learning, and computer vision. He is the co-author of the book entitled ¡°Handbook of Multibiometrics¡± which will be published by Springer in 2006.