Tattoos moved from only being available in a hospital, to a sign of intimidation and rebellion. Now, they are a norm in society and almost every knows someone who has one. An National Institute of Standards and Technology is now working to help body art become a form of identification through cataloging.
“Given the number and variety of tattoos, though, how to describe and catalog them? Clearly this is an area where technology can help, but it’s also one of those ‘fuzzy’ problems that challenges the limits of artificial intelligence.”
The NIST recently held a workshop called the NIST’s Tattoo Recognition Technology Challenge. The goal was to challenge the minds participating in the workshop to develop “automated image-based tattoo matching technology.” The process has been done manually for years but agencies like the FBI are looking for a more efficient way of going about it.
“State-of-the-art algorithms fared quite well in detecting tattoos, finding different instances of the same tattoo from the same subject over time, and finding a small part of a tattoo within a larger tattoo,” said NIST computer scientist Mei Ngan, according to the article.
The problem emerged when similar tattoos were found on multiple people. The algorithm also could not pull images from a sketch or any other source, it strictly went off of photos only.
“Among the systems demonstrated was “GARI” – A Gang Tattoo and Graffiti System (PDF) developed by Purdue University that collect gang graffiti and gang tattoos images, analyzes and interprets them, and provides access to law enforcement via a mobile application,” according to the article.
Further concerns about developing technology such as this lay within the boundaries of privacy. If hacked, the database could release information that would allow other individuals to target specific people based on their body art. As technological advancements continue privacy will always be one of the major concerns.
Read the full story here.