FBI Upgrades to Faster, More Accurate Fingerprint Identification System

The FBI today said it's made a long-awaited switch from its Automated Fingerprint Identification System (AFIS) to an upgraded, faster one the FBI calls Advanced Fingerprint Information Technology (AFIT). The AFIT replacement prepares the way for going beyond fingerprint identification to other biometrics, including latent palm prints and facial recognition, the next step in the FBI's multiyear effort called the Next Generation Identification (NGI) system.

"With the new system, we increase speed and accuracy of information," says John Traxler, the program manager for NGI in the FBI's Clarksburg, W.Va., facility which supports the core mission to match fingerprints submitted electronically by law enforcement against those stored and cataloged in the FBI's database in order to help solve criminal and civil cases.

FOR MORE ON SECURITY: 20 hot IT security issues

The old AFIS fingerprint-matching system took up to two hours to respond to a fingerprint pattern-matching request in criminal cases and 24 hours for civil cases, says Traxler. "Our goal for criminal prints is now 10 minutes, and civil, 15 minutes," says Traxler.

The faster fingerprint-matching program is all part of the NGI program, which started three years ago. The main contract for that was awarded to Lockheed Martin. The NGI program has included changes such as delivery of 900 new workstations to FBI personnel involved in fingerprint identification. The key to the AFIT system is a new fingerprint-identification algorithm based on technology supplied by subcontractor MorphoTrak. The biometric pattern-matching algorithm allows much faster and more accurate searches of prints stored in the FBI databases for this purpose.

According to Traxler, AFIS was only about 92% accurate in fingerprint pattern-matching, but AFIT has been benchmarked for at least 99% accuracy. He adds now that AFIT is up and running, the FBI will be able to move forward on some future goals.

"We're adding new biometric modalities, latent palm prints and facial recognition and iris [recognition]," he says, with the expectation that this next phase of evolving the FBI's identification system is expected to be completed by 2014.

Read more about data center in Network World's Data Center section.

Subscribe to the Security Watch Newsletter

Comments