AI Challenges Uniqueness of Fingerprints

Columbia University researchers use AI to identify similarities in different fingerprints of the same person, potentially revolutionizing biometrics and forensic science.

• Researchers from Columbia University have used an AI tool to challenge the long-standing belief that each fingerprint is unique, finding that prints from different fingers of the same person can be similar.
• The AI tool was trained on a database of 60,000 fingerprints and was able to identify, with 75-90% accuracy, whether prints from different fingers came from one person.
• The AI tool did not use traditional methods of fingerprint analysis, instead focusing on the orientation of the ridges in the center of a finger.
• The findings could potentially impact both biometrics and forensic science, potentially improving forensic efficiency by more than tenfold.
• Despite the promising results, more research is needed, and the tool is not yet suitable for use in court cases.

3 Articles

TechSpot Study Finds BBC