Science Editorial, January 10 (EFE).- Engineers at Columbia and the American University at Buffalo have developed a new fingerprint analysis using artificial intelligence (AI) that overturns a long-held belief in forensic medicine that there are never two fingerprints. Similar fingerprints. , not even on different fingers of the same person.
The findings, reported this Wednesday by the journal Science Advances, show with 99.99% confidence that fingerprints from any two fingers of the same person are much more similar than previously thought.
Basics of solving crimes
Fingerprints are essential in crime labs and in billions of mobile phones worldwide for digital authentication, however, currently, all technologies in this area are designed under the premise that no two fingerprints are the same.
To date, fingerprints are not useful in situations where the available prints are from 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 and the University of Buffalo, has shown that it is possible to overcome this limitation by analyzing characteristics of fingerprints that were not studied. now..
Guo and his colleagues scoured a public US government database of about 60,000 fingerprints and fed them in pairs into an artificial intelligence-based system called the Deep Contrast Network.
Sometimes the pair was with the same person (but with different fingers) and sometimes with different people.
The engineers, without prior forensic knowledge, extracted fingerprint representation vectors from 525,000 images using a deep neural network and made a surprising discovery: fingerprints from different fingers of the same person are extremely similar.
Ki, in the mountain range
They discovered that the orientation of the stripes near the center of the print (the most prominent area of the print) explains this similarity, and that this pattern holds for all pairs of fingers in the same person.
The model has been successfully tested with women of various gender and ethnic groups.
“We hope this additional information can help prioritize leads when there are multiple possibilities, exonerate innocent suspects, or even generate new leads for unsolved cases,” Guo said in a statement from Columbia University.
The researcher also emphasizes that his invention can improve the convenience and accessibility of digital authentication technologies.
(c) EFE Agency
This is a new record that scientists from the Korea Fusion Energy Institute (KFE) have…
Damages associated with drought, floods, hail and other increasingly violent events are expected to increase…
An estimated 9 million people in the United States are still waiting for their final…
The death of seven humanitarian workers from the American NGO World Central Kitchen in an…
Today, at one o'clock in the morning, Gamer updates it Boutique de Fortnite Through the…
The Basic Instinct and Casino actress looks back at a time in Hollywood when adapting…