Department of Computer Science and Engineering Skip to Content Michigan State University logo
Biometrics Research Group banner

What is Biometrics?

The field of biometrics examines the unique physical or behavioral traits that can be used to determine a person’s identity. Biometric recognition is the automatic recognition of a person based on one or more of these traits. The word “biometrics” is also used to denote biometric recognition methods. For example, fingerprint, face, or iris biometric features are sometimes described as single biometrics. Biometric technology can prevent fraud, enhance security, and curtail identity theft.


Applications

Forensics

Biometric recognition techniques have been used in forensic applications for over 100 years: they have aided criminal investigations, identified disaster victims, and helped to locate missing children. Biometric recognition systems can spare investigators the time-consuming process of sorting through thousands of files by hand. In some applications, they can also provide a degree of accuracy that is difficult to achieve with the human eye. Even among experts, human classification or recognition of biometric traits is not always possible to achieve.

Government

Forged or stolen identification cards are a common security problem all over the world. According to the United Kingdom’s Identity and Passport Service, over 290,000 U.K. passports are lost or stolen each year. Some international airports are adopting iris, fingerprint, or face recognition systems to prevent individuals from entering a country using false credentials. In some facilities, biometric scans offer air travelers the convenience of expedited passenger check-in. Driver’s licenses, ID cards, and passports are beginning to include biometric information as an extra security feature.

Commercial

The need to protect personal information has led to the deployment of numerous commercial biometric recognition systems. In the U.S. alone, identity theft and credit card fraud strike millions of consumers every year, with an annual cost of around $50 billion dollars. More and more personal and private data is stored in electronic form: medical history, credit card information, vital statistics, and more. Biometric recognition techniques can add an extra layer of security to traditional password-based systems or replace them altogether. Advances in biometric recognition technology have led to low-cost, compact sensors, making it possible to deploy biometric systems in grocery stores, at ATMs, in laptop computers, and even at Walt Disney parks.


Dubai Airport

UIDAI

OBIM

Disney World

Apple iPhone 5s

Micro Loans in Malawi

Embedded Biometric Device

Biometric ATMs


Biometric recognition systems

Biometric recognition systems require traits that are unique to each individual and do not change much over time. The most popular traits used in biometric systems are fingerprint, face, and iris. Other traits include palm, dental, voice, gait, and even “soft” biometric characteristics like scars or tattoos.

Multimodal biometric systems

Multimodal biometric systems use more than one trait for person recognition. For example, a system might use both fingerprint and face biometrics to authenticate a person’s identity. This technique, also known as multibiometrics, can enhance security or resolve difficulties that some users experience with the enrollment stage of biometric recognition. Multibiometric recognition techniques can also use multiple matching methods for the same trait (e.g., a single fingerprint analyzed with two different matching systems) or multiple occurrences of a trait (e.g., more than one fingerprint).

Verification versus identification

There are two types of recognition used in biometric systems: verification or identification. Verification confirms whether a person is who they claim to be. It is a 1:1 match-or-no-match scenario. Identification is more difficult. The system must recognize one person from all others enrolled in a database (1:N matching scenario).

Advantages over ID cards and passwords

Compared to biometric identification, traditional methods involving only ID cards or passwords are not as reliable. Passwords can be lost or stolen and ID cards can be forged. Biometric recognition offers the following advantages:

  • Users do not need to remember a password or carry an ID card
  • The person to be identified must be physically present at the point of identification
  • Biometric systems are much harder to foil
  • Biometric traits cannot be stolen

How does biometric recognition work?

A biometric recognition system is a pattern recognition system. During biometric recognition, biometric traits are measured and analyzed to establish a person’s identity. This process involves several stages.

Enrollment

During enrollment, a user’s physical or behavioral trait is captured with a camera or sensor and placed in an electronic template. This template is securely stored in a central database or a smart card issued to the user.

Recognition

During recognition, a sensor captures a biometric trait. The trait is then analyzed with an algorithm that extracts quantifiable features, such as fingerprint minutiae or face shape. A matcher takes these features and compares them to an existing template in the enrollment database.


Further reading

A. K. Jain, A. Ross, and K. Nandakumar, Introduction to Biometrics, Springer, 2011.

D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition, Second Edition, Springer, 2009.

A. K. Jain, P. Flynn, A. Ross, Handbook of Biometrics, Springer, 2007.

A. K. Jain, "Biometric recognition: Q&A", Nature, Vol. 449, pp. 38-40, Sept. 6, 2007.

A. Ross, K. Nandakumar and A.K. Jain, Handbook of Multibiometrics, Springer, 2006.

A. K. Jain and S. Pankanti, "A Touch of Money", IEEE Spectrum, vol. 43, no. 7, pp. 22-27, July 2006.

S. Z. Li and A.K. Jain, Handbook of Face Recognition, Springer, 2005.

A. K. Jain, A. Ross, and S. Prabhakar, "An Introduction to Biometric Recognition", IEEE Trans. on Circuits and Systems for Video Technology, Special Issue on Image- and Video-Based Biometrics, vol. 14, no. 1, pp. 4-20, January 2004.

A. K. Jain and A. Ross, "Multibiometric Systems", Comm. ACM, vol. 47, no. 1, pp. 34-40, January 2004.

A. K. Jain, L. Hong, and S. Pankanti, "Biometric Identification", Comm. ACM, vol. 43, no. 2, pp. 90-98, February 2000.

bottom graphic