Police may soon be able to catch criminals by the ink they are sporting.

Computer scientists are developing a new program that will be able to identify suspects by their tattoos and match them to photos in police databases or on social media.

Automatic identification through recognition of body art could provide a much needed breakthrough in detective work, often thwarted by grainy footage from surveillance videos that make it difficult to see a criminal’s face to use facial recognition.

‘Those photos are often so bad that face recognition wouldn’t come even close’ to finding a match in a database, Terrance Boult, a computer science professor at the University of Colorado, explained to Live Science.

To rectify this problem, Boult worked with a team of researchers to develop a computer program that reviews body ink, scars, moles and visible skin markings in photos.

The program scans images for these identifiable skin symbols and then looks for people bearing the same markings in a photo database.

The program is designed to pick up patterns in tattoos and could even link together members of gangs, who often share body tags.
Though this isn’t the first program to examine body markings for identification, the computer program was designed to better handle low quality photos, like those taken from a smart phone.

Read More