Researchers have discovered that not all fingerprints are unique and distinct.
Engineers from the American universities of Columbia and Buffalo created new fingerprint analysis using artificial intelligence (AI) that challenges the long-held belief in forensic science that no two fingerprints are ever the same, even on different fingers of the same person.
The discovery was reported this Wednesday by the magazine. Science Progress, demonstrated with 99.99% confidence that The prints of any two fingers from the same person are much more similar than previously thought.
Fingerprints are needed in crime labs to solve cases, and on billions of mobile phones around the world for digital authentication, although all technology in this area is currently being developed with the understanding that no two fingerprints are alike.
To date, fingerprints are of no use in situations where fingerprints other than those recorded are available, such as at a crime scene.
However, a study conducted Gabe Goengineering student at Columbia University, along with other researchers from the same university and the University at Buffalo, showed that this limitation can be overcome by analyzing previously unexplored characteristics of fingerprints.
Guo and his colleagues found a public US government database with some 60,000 fingerprints and fed 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.
Engineers, with no prior forensic knowledge, extracted fingerprint representation vectors from 525,000 images using deep neural networks and made an amazing discovery: Fingerprints from different fingers of the same person are extremely similar.
They found that the orientation of the ridges (the most prominent area of the print) near the center of the prints accounts for much of this similarity, and that this pattern holds true for all pairs of fingers from the same person.
The model has been successfully tested on women of different genders and racial groups.
“We hope this additional information will help prioritize leads when there are many possibilities, exonerate innocent suspects, or even create new leads in unsolved cases,” Guo said in a statement from Columbia University.
The researcher also emphasizes that his discovery can increase the convenience and accessibility of digital authentication methods.
(According to EFE)