Engineers from Columbia and Buffalo universities have created a new fingerprint analysis using artificial intelligence (AI) that overturns the long-held belief in forensic medicine that no two fingerprints are the same, even on different digits of the finger. .

The finding, reported Wednesday by the journal Science Advance, showed with 99.99% confidence that the fingerprints from two fingers of the same person are much more similar than previously thought.

Basics of Crime Solving

Fingerprints are essential in crime labs to solve cases, and in billions of mobile phones around the world for digital authentication, although for now all technologies in this area are designed with the assumption that this is not the case. There are two identical fingerprints.

Until now, fingerprints are not useful in situations where the available prints come from fingers other than those recorded, such as at a crime scene.

However, a study promoted by Gabe Guo, an engineering student at Columbia, along with other researchers from the same university and the University at Buffalo, has shown that it is possible to overcome this limitation by analyzing features of fingerprints that have not been previously studied . now. .

Guo and his colleagues found a public U.S. government database containing about 60,000 fingerprints and entered them in pairs into an artificial intelligence-based system known as a deep contrast network.

Sometimes the pairs were from the same person (but with different fingers) and sometimes from different people.

Engineers, with no prior forensic knowledge, extracted fingerprint representation vectors from 525,000 images using deep neural networks and made a surprising discovery: fingerprints from different fingers of the same person look extremely similar.

The key, in the back

They found that the orientation of the ridges (the most prominent area of ​​the print) near the center of the prints explained much of this similarity, and that this pattern holds for all pairs of fingers on the same person.

The model has been successfully tested in women of different genders and racial groups.

“We hope this additional information can help prioritize leads when there are many possibilities, exonerate innocent suspects, or even create new leads for unsolved cases,” Guo said in a statement released by Columbia University.

The researcher also emphasizes that his discovery can improve the convenience and accessibility of digital authentication techniques. (JO)