Site   Web

July 4, 2013

Penn State Develops Fingerprint Identification Software

Even 20/20 vision isn’t perfect when it comes to evaluating fingerprints, so Penn State Researchers have developed a fool-proof way to consistently analyzing prints.

Fingerprints usually undergo environmental weathering and smudging. The condition of a fingerprint affects how reliable a match can be between a collected print and prints on record. Knowing a fingerprint’s dependability can minimize the chance of a wrongful or delayed conviction,” according to a Penn State press-release.

Researchers have created a process in which three different computer programs are utilized to properly identify the person behind the print.

What’s accomplished is evaluation of a print “to a degree finer than any human can accomplish,” says the university.

“The quality of a fingerprint can be graded finer than on a zero, one, two, three scale,” explained Akhlesh Lakhtakia, a professor of engineering science and mechanics at Penn State. “Two point three per cent is worse than fifteen per cent, but both could be graded as a zero by the naked eye. Humans can’t grade finer than the zero to three scale. But computers can.”

The three separate computer programs include the FBI’s Universal Latent Workstation, open-source image editor GIMP and a simple custom program written in Mathematica to count pixels.

The process is fairly simple.

First, investigators photograph the fingerprint and run it through the Universal Latent Workstation, which creates a simplified map of the fingerprint and designates colors to the print – black for the background, defined areas with white, and “debatable” regions in yellow and blue.

After that, GIMP turns the fingerprint into an RGB image file. Since RGB values are stored by the computer as number clusters, the photo can be translated in to binary sequences.

This is where the Mathematica comes in. The program calculates the total percentage of white pixels, creating a grading scale ranging from zero to 100.

A high-quality fingerprint would have a high number of white pixels, while a potentially unreliable print would mostly appear in yellow and blue,” says the school’s news release.

Penn State researchers believe the simplicity and speed of its new fingerprint grading system may “help standardize fingerprint quality assessment in an inexpensive, efficient manner.”

Lakhtakia said researchers are still working to identify if there is “false detail created by development techniques,” although it’s not likely.

We would obviously have to prove it,” he said.