For a long time, we have known that the front of each finger of a human being is unique from the front of another finger. However, this claim is now being challenged with the help of artificial intelligence.
A team at Columbia University in the US trained an artificial intelligence tool to examine 60,000 fingerprints to determine which fingerprints belonged to the same person.
After repeated research, the researchers released a scientific article in which they said: “We show above 99.99% confidence that fingerprints from different fingers of the same person share very strong similarities.”
Researchers believe that artificial intelligence was analyzing fingerprints in a different way than traditional methods. It focuses on the direction of the lines in the middle of the finger rather than how the individual lines terminate, known as minutiae.
Professor Lipson says: “So clearly it’s not using the traditional markers that forensics have been using for decades. It seems to be using something like the angle of rotation.”
Researchers claim that the technology can identify with 75 to 90 percent accuracy whether different fingerprints belong to the same person. But they can’t say for sure how it works.
Usage in forensic
Columbia University’s research findings have the potential to impact both biometrics and forensic science.
For example, if an unknown thumbprint is found at crime scene A, and an unknown print of a lady finger is found at crime scene B, so currently the two cannot be forensically linked to the same person because fingerprint biometrics are based on the traditional assumption that no two fingerprints, even from the same person, are alike but an AI tool may be able to identify it.
The similarity
The researchers have to say after a long analysis
“Now that we have established the existence of a strong similarity among a person’s 10 fingerprints, regardless of which fingers we consider, we examine the specific features that contribute to this similarity.”