The belief that all fingerprints are unique is so well accepted that crime novels and TV shows riff on it. Recent AI research has challenged this notion, at least regarding the fingerprints on different fingers of the same person.
Undergrad researchers at Columbia Engineering found that while the branching and endpoints in the fingerprint ridges might vary, the angles and curvature at the center of the fingerprint could be the same across an individual.
To determine this, the students used a deep contrastive network and a US government database of 60,000 fingerprints to study commonalities in fingerprints. They fed pairs of prints to a neural network, with some coming from the same person and others from different individuals.
The network eventually became able to identify if prints were from the same person to an accuracy of 77 percent. That accuracy increased when multiple pairs of prints were presented.
The team initially had no idea how the network was able to identify whether the prints belonged to the same person. To the human eye, the fingerprints certainly did not appear similar.
In order to understand that it was merely identifying the angles and starting points of the ridges, they had to study the AI system’s decision process. Thus, the team concluded that the AI was using an unexpected forensic marker.
As it turns out, humans can be so set in their processes not only when it comes to identifying prints but also identifying science. The first journal the team submitted their results to rejected them with the conclusion: “It is well known that every fingerprint is unique,” according to the university.
Engineering Professor Hod Lipson pushed to get the story published, citing the number of cold cases that could be solved using this new information.
While the system’s accuracy is not sufficient to officially decide a case, it is believed it can help prioritize leads in ambiguous situations.
“Many people think that AI cannot really make new discoveries – that it just regurgitates knowledge,” said Lipson. “But this research is an example of how even a fairly simple AI, given a fairly plain dataset that the research community has had lying around for years, can provide insights that have eluded experts for decades.”
Their results are to be published in Science Advances on January 12 at 19.00 UTC. Another publication broke the embargo so we have clearance to run this piece earlier than planned, but the research is not yet ready. ®
- SEO Powered Content & PR Distribution. Get Amplified Today.
- PlatoData.Network Vertical Generative Ai. Empower Yourself. Access Here.
- PlatoAiStream. Web3 Intelligence. Knowledge Amplified. Access Here.
- PlatoESG. Carbon, CleanTech, Energy, Environment, Solar, Waste Management. Access Here.
- PlatoHealth. Biotech and Clinical Trials Intelligence. Access Here.
- Source: https://go.theregister.com/feed/www.theregister.com/2024/01/11/ai_fingerprints_unique/
