NIST studying biometric matching algorithms for tattoo database
According to a report in ITNews, computer scientists at the National Institute of Standards and Technology (NIST) will soon begin the second round of an independent study into which biometric matching algorithms work best for pairing tattoos with criminal suspects, unidentified victims, and alleged gang members.
In a presentation at the Biometric Institute’s Asia Pacific conference, NIST’s Mei Ngan and Patrick Grother said that in the US, tattoos are often used by law enforcement to identify persons of interest but national databases rely on subjective manual text descriptions to conduct searches. Ngan and her team have been testing image recognition algorithms on a small subset of tattoos to see how well they can match images in different settings, partial tattoos to whole tattoos, and even similar tattoos on different persons.
“A suspect might be captured in video surveillance, and we can’t see their face but we can see part of their tattoo out of the bottom of their shirt,” Ngan said.
The NIST ‘Tatt-C’ experiment saw NIST release a test set of tattoo data and a series of use cases for volunteers MorphoTrak, Purdue, FraunhoferIOSB, MITRE and Compass to test their solutions on. The top ranked MorphoTrak registered a 99.4 accuracy rate.
This summer, NIST will begin a more rigorous round of internal testing using much larger data sets, and uniform hardware. “Instead of giving the information out to the developers, the providers will send their software to NIST to be evaluated,” Ngan said.