Computer Tests Proves Handwriting Analysis Is Legitimate

Is your handwriting so distinctly different from anyone else's that an expert could tell whether you — and you alone — scrawled a note that you may not even remember writing?

Could a computer do the same thing by simply "looking" at a few simple features?

The answer is yes, and no one is more surprised than the computer scientist who produced the first scientific evidence that handwriting is individualistic. No one else writes exactly like you. Like your fingerprints, your handwriting is yours and yours alone.

And that's a matter of great interest to the courts.

In a key ruling in 1993, the U.S. Supreme Court established guidelines for the admissibility of scientific evidence, saying the evidence must be backed up by scientific experimentation. As a result, handwriting analysis in recent years has routinely been thrown out by the courts because no one could prove it is scientifically valid.

So the National Institute of Justice turned to Sargur Srihari, a computer scientist and director of the Center of Excellence in Document Analysis and Recognition at the University of Buffalo.

"The motivation was to establish whether everybody's handwriting is individualistic," Srihari says. "Surprisingly, this fact had not been established with scientific experimentation."

Reading Handwritten Letters

But it has now, thanks to the efforts of Srihari and several colleagues. On April 29th, the U.S. District Court for the Eastern District of Pennsylvania listened to Srihari describe the evidence his team has compiled and then allowed expert testimony concerning handwritten documents to be introduced as evidence.

Srihari says that when he first started working on the project he didn't have a clue as to whether handwriting is individualistic. But he knew something about computers, and his track record in computer analysis of handwriting is pretty impressive.

He led the university's team that began tackling a similar problem for the U.S. Postal Service more than a decade ago. Automation was the key to streamlining the postal service, but how do you automate handwritten letters? Srihari thought he could do it with a computer program, despite skepticism at the post office.

"They didn't believe it was possible," he says. Some noted that they had trouble even reading their own handwriting, so how could a computer do it?

But nobody doubts it now. The software developed in Srihari's lab is now in use at all postal centers across the country, and it can read nearly 75 percent of handwritten addresses. The rest are kicked out of the sorter and require human intervention.

But 75 percent is impressive enough to have caught the attention of the National Institute of Justice, which asked Srihari if he could use his expertise to develop a scientific basis for determining whether handwriting analysis is real or mumbo jumbo.

Marks That Mark Us

His team collected handwriting samples from 1,500 persons across the country of various ages and ethnic backgrounds.

"We tried to make it as representative [of the general population] as possible," he says.

  • 1
  • |
  • 2
Join the Discussion
blog comments powered by Disqus
You Might Also Like...