Engineers from the American universities of Columbia and Buffalo have created a new fingerprint analysis Through artificial intelligence (AI), which overturns the long-held belief in forensic medicine that no two fingerprints are ever alike, even from different ones of the same person. Not even on the fingers.
The discovery, reported this Wednesday by the journal Science Advances, showed that with 99.99% reliability, any two fingerprints of the same person they are too similar As much as was thought.
Basics of solving crimes
Fingerprints are essential in crime laboratories for solving cases and in billions of mobile phones around the world for digital authentication, however, for now, all technologies in this area are designed on the basis that No two fingerprints are alike.
To date, fingerprints are not useful in situations where the available prints are those of fingers other than those recorded, such as at a crime scene.
However, a study promoted by Columbia engineering student Gabe Guo, along with other researchers from the same University at Buffalo, has shown that it is possible to overcome this limitation. Analyzing Unstudied Characteristics Fingerprints so far.
Guo and his colleagues found a public US government database with about 60,000 fingerprints and entered them in pairs into an artificial intelligence-based system known as a deep contrast network.
Sometimes the pairs belonged to the same person (but with different fingers) and sometimes to different people.
Without prior forensic knowledge, engineers 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 are extremely similar.
key, in lines
He found that the orientation of the ridges near the center of the print (the most prominent area of the print) explained much of this similarity, and that This pattern applies to all pairs of fingers of the same person,
The model has been successfully tested with women of different genders and racial groups.
“We hope this additional information Prioritizing leads may help When there are multiple possibilities, it can lead to the acquittal of innocent suspects or even generate new leads for unsolved cases,” Guo said in a statement from Columbia University.
The researchers also emphasize that their discovery could improve the convenience and accessibility of digital authentication technologies.