US university uses AI to prove our fingerprints are not unique

Researchers at Columbia University in the United States have challenged the belief that every fingerprint is unique by using artificial intelligence (AI). They trained an AI tool to analyze 60,000 fingerprints to determine if it could accurately identify fingerprints belonging to the same person.

The AI tool demonstrated an accuracy rate of 75-90% in identifying whether fingerprints from different fingers belonged to the same individual. This finding raised questions about the traditional methods of fingerprint analysis.

Professor Hod Lipson, who supervised the study, explained that the AI appeared to analyze fingerprints differently from conventional forensic methods. Instead of traditional markers, it seemed to consider factors like the curvature and angle of swirls in the fingerprint’s center.

While unique fingerprints have been a long-standing assumption, Professor Graham Williams of Hull University suggested that this notion was not set in stone, stating that no two people had demonstrated identical fingerprints to date.

The surprising findings of the study were initially rejected by an unnamed forensics journal, but Professor Lipson emphasized their importance. He suggested that these findings could potentially lead to the review of cold cases and the exoneration of innocent individuals.

The research’s implications extend to both biometrics and forensic science, according to the BBC report.