A recent study led by engineers at the American universities of Columbia and Buffalo has challenged the long-held belief that no two fingerprints are alike, even among different fingers of the same person. Using artificial intelligence, the study analyzed a US government public database with about 60,000 fingerprints, some from the same person and others from different people.
The research published in the Science Advance magazine found that fingerprints from any two fingers of the same person are much more similar than previously thought, with a 99.99% confidence level. This discovery is groundbreaking as it has the potential to revolutionize forensic medicine, where fingerprints are essential in crime labs to solve cases and on billions of mobile phones around the world for digital authentication.
The students leading the study, including Gabe Guo, an engineering student at Columbia, and other researchers found that the key to this similarity was in the ridges, the most prominent area of the fingerprint. They observed that the orientation of the ridges near the center of the fingerprints explained much of this similarity, and that the pattern was repeated in all pairs of fingers of the same person.
This study opens up new possibilities for fingerprint analysis and could have a significant impact on forensic and digital authentication technologies.