Tattoo designs that link the wearer to criminal organizations are nothing new for law enforcement. They’ve been used as a means of shedding light on the underworld for decades, but it’s only recently that technology has revolutionized tattoo identification in the way it did fingerprinting.
Digital civil liberties nonprofit Electronic Frontier Federation recently published a breakdown of related experiments carried out by the Federal Bureau of Investigation (FBI) and National Institute for Standards and Technology (NIST). Beginning in the 2014, the two agencies collaborated on a series of tests which sought to fine-tune digital tattoo recognition. The project’s codename: Tatt-C.
— Federico Soler (@Fede_Soler_Mej) April 25, 2016
Considering the results, it appears that law enforcement already possesses the technology capable of rolling out such programs immediately. Approaching the tool in five different ways, NIST and the FBI found that they could easily use the system to yield accurate tattoo identification. One such time-saving measure would be automatization of identifying such tattoos in the troves of crime scene photos that police struggle to dig through.
“Tatt-C’s research team reported back that three different organizations’ algorithms could detect a tattoo in an image with more than 90% accuracy. The private biometric technology company MorphoTrak (a subsidiary of Safran) claimed the best result; their algorithm was able to detect whether an image contained a tattoo or not with 96.3% accuracy.”
Showing similar levels of success, computers can now competently link photos taken at various parts of the subject’s lifetime through distinguishing tattoos — despite any changes the person may have undergone in physical appearance. Similarly, if only a select portion of a tattoo is visible, an automated process can link it up to its full design. Both of these techniques could prove extremely useful to investigators.
“Let’s say a cop is questioning someone on the street who refuses to provide an ID card. The officer could run a photo of one of the person’s tattoos through a database to find a photo of the same tattoo captured during a previous arrest. One situation NIST imagines is applying tattoo recognition technology to video surveillance of a robbery in which the suspect is wearing a mask but a neck tattoo is visible.”
Not all of the tests produced positive results. One technology which sought to find similarities between tattoos and other representations of the same symbol in other media failed more than 80 percent of the time. Another means of identification — perhaps the most ambitious — also failed when it attempted to more generally link together symbols that may or may not be reproduced exactly the same on each individual. EFF was extremely critical of this technique, as well as the fact that as many as 15,000 such gang tattoo images had been released to private companies.
“This should raise bright red flags for those concerned about religious freedom, especially in light of how authoritarian governments have used tattoos to oppress religious minorities. Nazi Germany’s use of tattoos to track Jews during the Holocaust comes to mind. Indeed, the six-pointed Star of David was one of the images used during the NIST experiments. However, in that case, the star also serves as the symbol of the Gangster Disciples, a Chicago street gang. So even when law enforcement is attempting to use tattoos to investigate gangs, people who are simply expressing their religion could be labeled as affiliates of criminal gangs.”
— Scott Sparrow (@ChirpyScott) May 14, 2016
Many of the tattoo design recognition technologies have already been implement in law enforcement institutions around the country. EFF noted the MorphoTrak and DataWorks both have contracts with the state of California, and an app from Purdue University has already facilitated basic use of the method for police across the state of Indiana.
[Image via Kevork Djansezian/Getty Images]