Sargur Srihari developed a software that can determine the rarity of a particular fingerprint and how likely it is to belong to a particular crime suspect. Srihari combined machine learning with the ability to automate the extraction of specific patterns or features in a fingerprint. He compared the data with databases of fingerprints, which gave him a idea how likely it would be that a specific fingerpint would randomly match another in a database of a specific size.
When we look at DNA, we can say that the likelihood that another person might have the same DNA pattern as that found at a crime scene is one in 24 million," Srihari explains. "Unfortunately, with fingerprint evidence no such probability statement can be made. Our research provides the first systematic approach for computing the rarity of fingerprints in a scientifically robust and reliable manner."
According to Srihari, coming up with fingerprint evidence gets difficult when fingerprints are invisible to the naked eye and have to be lifted using either powder or ultraviolet illumination and the following analysis of what was found is likely to confirm identity, unlikely to confirm identity or ends up as an "inconclusive" result. "A probability statement as to how rare a specific finger print is would be a dramatic improvement in the way that such evidence is currently described to juries," Srihari said.
Unfortuantely, a press release by the University of Buffalo does not provide any results in numbers. Emails sent to Srihari have not been answered yet.