If you’re a fan of true crime or ever read Nancy Drew (or Hardy Boys) growing up, you probably have the idea that fingerprints will be the thing that nails people for crimes more often than not.
And why?
Because they’re totally unique, right?
Well…not quite.
For this new study, in fact, researchers used a neural network to identify different fingerprints belonging to the same person up to 77% of the time.
It was led by engineering senior Gabe Guo at Columbia University.
“We suggest that the intra-person fingerprint similarities are of interest not only because they challenge long-held beliefs but also because this similarity could help improve the ability to find leads for investigations when the fingerprints obtained from crime scenes are different fingers than the fingerprints already on file.”
The researchers hope this information could help law enforcement going forward.
“We hope this additional information could help prioritize leads when many possibilities exist, help exonerate innocent suspects, or even help create leads for cold cases.”
They started with a US database of around 60,000 fingerprints made up of 10-finger sets from individual subjects. They fed the prints into neural networks, which are a kind of AI, and it began to find similarities.
“The AI was not using ‘minutiae,’ which are the branchings and endpoints in fingerprint ridges – the patterns used in traditional fingerprint comparison. Instead, it was using something else, related to the angles and curvatures of the swirls and loops in the center of the fingerprint.”
They found that although each fingerprint on the same hand was still unique, there were enough similarities between them for the AI to make a match. Specifically, the orientation of the ridges in the center of the print is similar for the different fingers of the same individual.
That said, the research is still in its infancy and its ability to match different prints to one person isn’t yet good enough to hand over to law enforcement.
It could be used to narrow down suspects, though.
“Just imagine how well this will perform once it’s trained on millions, instead of thousands of fingerprints.”
They believe tech companies may be interested, too, since any finger would do for a fingerprint scanner, and this team is excited to take this research further.
“Many people think that AI cannot really make new discoveries – that is just regurgitates knowledge. But thi 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.”
I’m still not convinced about AI, but this is pretty cool.
Unless you’re a criminal. Then, I guess tough luck.
If you found that story interesting, learn more about why people often wake up around 3 AM and keep doing it for life.