AI Study Claims Human Fingerprints Aren’t Actually Unique

Key Points:

  • New research challenges the long-held belief that fingerprints are unique, suggesting that AI can identify whether prints from different types of fingers come from the same person with high accuracy.
  • The AI model focused on angles and curvatures of swirls at the center of fingerprints, rather than traditional minutiae, leading to potential implications for criminal investigations and innocent people.
  • The claims of the research have faced criticism from forensic scientists, with one professor arguing that the findings do not necessarily disprove the existing understanding of fingerprints’ similarities and differences.

Summary:

The research suggests that fingerprints may not be as unique as previously believed. By using an AI model trained on a database of 60,000 fingerprints, the researchers found that the AI was able to identify whether prints from different types of fingers came from the same person with 75 to 90 percent accuracy, using angles and curvatures of the swirls at the center, rather than the traditional minutiae. The claims have faced pushback from forensic scientists, with one professor arguing that the findings are not necessarily new and do not disprove current forensic techniques.

DAILY LINKS TO YOUR INBOX

PROMPT ENGINEERING

Prompt Engineering Guides

ShareGPT

 

©2024 The Horizon