BUFFALO, N.Y. – Crime scene forensic analysis has long
functioned on the premise that a person's unique identity is hidden
in the tiny loops and swirls of their fingerprints, but teasing
that information out of the incomplete prints left at crime scenes
is still an inexact science, at best.
Now, a University at Buffalo professor has developed a way to
computationally determine the rarity of a particular fingerprint
and, thus, how likely it is to belong to a particular crime
The paper, "Evaluation of Rarity of Fingerprints in Forensics,"
will be presented by Sargur N. Srihari, PhD, co-author and SUNY
Distinguished Professor in the UB Department of Computer Science
and Engineering, at the Proceedings of Neural Information
Processing Systems conference today in Vancouver.
By combining machine learning with the ability to automate the
extraction of specific patterns or features in a fingerprint and
then comparing it with large databases of random fingerprints,
Srihari and co-researchers are able to come up with a probability
that a specific fingerprint would randomly match another in a
database of a given size.
The UB research is the first attempt to determine the rarity of
a fingerprint using computational tools.
"Current procedures for forensics do not provide a measured
accuracy for fingerprint analysis," says Srihari.
The UB research lays the groundwork for the development of
computational systems that could, for the first time, quickly and
objectively reveal just how meaningful is the fingerprint evidence
in a given case.
The research directly addresses some of the profound shortfalls
identified by the National Academy of Sciences' Committee on
Identifying the Needs of the Forensic Science Community, which
Srihari served on with other national experts from 2007-2009. Some
of the committee's recommendations dealt specifically with
fingerprints, including the need for baseline standards to be used
with computer algorithms to map, record and recognize features in
This month, Srihari also authored a feature article, "Beyond
CSI: The Rise of Computational Forensics," for IEEE Spectrum (http://spectrum.ieee.org/computing/software/beyond-csi-the-rise-of-computational-forensics)
on this new field.
"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."
Part of the difficulty is due to the intrinsic nature of
fingerprint evidence, he says, where fingerprints are invisible to
the naked eye and have to be lifted using either powder or
According to Srihari, two types of uncertainty are involved in
fingerprint analysis, similarity between two fingerprints and the
rarity of a given configuration of ridge patterns.
"Human examiners describe the results of their analyses in one
of three ways: likely to confirm identity, called
individualization, unlikely to confirm identity, called exclusion,
or inconclusive," he says. "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."
Forensic analysis depends on something called a likelihood
ratio, which is the ratio between the probability that the evidence
found at the scene and the known data – for example, a
suspect's fingerprint -- come from the same source and the
probability that they come from different sources.
The new method developed at UB uses machine learning, a type of
artificial intelligence where machines learn from examples, through
the use of statistics and probability. The UB researchers used
machine learning to predict the core point, usually the center in
the finger around which the ridges flow.
"In forensic analysis, the fingerprints are usually incomplete,"
Srihari explains. "Thus a guess has to be made as to which part of
the finger it came from. Our approach allows us to predict the core
point and thus orient the print for further analysis."
Srihari's co-author is Chang Su, a doctoral candidate in the UB
Department of Computer Science and Engineering in the School of
Engineering and Applied Sciences.
The research was supported by a grant from the U.S. Department
The University at Buffalo is a premier research-intensive
public university, a flagship institution in the State University
of New York system and its largest and most comprehensive campus.
UB's more than 28,000 students pursue their academic interests
through more than 300 undergraduate, graduate and professional
degree programs. Founded in 1846, the University at Buffalo is a
member of the Association of American Universities.