In Brief

The Fact of Fingerprints

Good old-fashioned fingerprints remain the most effective biometric available

By Scott Berinato

September 01, 2004CSO — In an era when technologists have tried to identify us with a scan of our eyeballs or our faces, the sound of our voices or even by the way we walk, good old-fashioned fingerprints remain the most effective biometric available.

A recent study by the National Institute of Standards and Technology confirms that fact. Fingerprint identification systems have approached 99 percent accuracy and, perhaps more importantly, a slim 0.01 false positive rateor only about one in 10,000 scans resulting in a misidentification.

The NIST study tested 34 fingerprint ID systems from 18 companies. About 25,000 people supplied about 50,000 sets of fingerprintsin all about 400,000 distinct digital images of digits. The best systems reached 98.6 percent accuracy for a single-print match. Predictably, the more prints that matched, the higher the accuracy rate. Two-finger matches were accurate 99.6 percent of the time. Four or more fingers, 99.9 percent.

NIST conducted the study under directives from the USA Patriot Act and the Enhanced Border Security and Visa Entry Reform Act. The hope is that the fingerprint ID systems used by the FBI can be shared with the Department of Homeland Security.

While the hype will focus on ever more imaginative biometrics, fingerprinting still works the best.

Other stories by Scott Berinato

$firstKeyword

RESOURCE CENTER
Loading...
VIRTUAL CONFERENCE
Security Directions: A Virtual Conference

Security Directions Available On Demand Sept. 30 - Dec. 30

Join us for a virtual event with candid, expert information on top security challenges and issues - all from the comfort of your desktop.

» Register Now

WEBCAST
Protecting PII: How to Work with IT to Manage Risk

Compuware Understand the critical nature of the test data privacy problem and get tips on how to work with IT to implement a test data privacy program.

» View this Webcast

Featured Sponsors