[iwar] Dissecting Handwriting Computer Tests Proves Handwriting Analysis Is Legitimate

From: Fred Cohen (fc@all.net)
Date: 2002-06-05 20:05:24
Next message: Fred Cohen: "[iwar] [fc:Heads-Up.To.Ashcroft.Proves.Threat.Was.Known.Before.9/11]"
Previous message: Fred Cohen: "[iwar] Stupid Things People Do"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]
Message-Id: <200206060305.g5635OY11576@red.all.net>
To: iwar@onelist.com (Information Warfare Mailing List)
Organization: I'm not allowed to say
From: Fred Cohen <fc@all.net>
Mailing-List: list iwar@yahoogroups.com; contact iwar-owner@yahoogroups.com
Precedence: bulk
Date: Wed, 5 Jun 2002 20:05:24 -0700 (PDT)
Subject: [iwar] Dissecting Handwriting Computer Tests Proves Handwriting Analysis Is Legitimate
Reply-To: iwar@yahoogroups.com
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: quoted-printable

http://abcnews.go.com/sections/scitech/DyeHard/dyehard.html

Dissecting Handwriting Computer Tests Proves Handwriting Analysis Is Legitimate

By Lee Dye Special to ABCNEWS.com

June 5 -- 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.

The software developed for the post office was modified somewhat to zero
in on differences in the handwriting. Such things as the spacing of
letters, and how the letters are slanted, and how "loops" in numbers and
letters are opened and closed, were easily recognized by the software.
There is considerable variation in how hard we press down when writing,
and the computer could detect that by the darkness of the letters.

The team ended up with 11 features that characterize the structure of
the writing, such as the size of margins and spacing of characters and
lines, and 512 features of individual letters and numbers. Two people
might make an identical "e," but it is less likely the same two people
would also make an identical "b," and so on.

"So we set up an experiment for our computer," Srihari says. "Could the
computer program tell whether two documents were written by the same
person, or two different people?"

In each case the researchers knew the answer, "and we wanted to see if
the computer could figure it out also."

The results were a bit astounding. If given a substantial document, say
a complete page of handwriting, the computer got it right 96 percent of
the time. Even if just given a couple of words, the computer still
nailed it more than 80 percent of the time.

"That's pretty high, and it's surprising because we were using pretty
simple features," Srihari says.

A human, properly trained, should do even better, he adds.

There are far more sophisticated features, like style of writing and
phrasing, that are much more difficult to analyze with software than the
simpler features used by the researchers. Yet they are routinely used by
handwriting experts.

Catching Fakes

One area that Srihari's research did not address is how hard, or easy,
it might be to fool the computer, or the expert. It might not be all
that difficult to trick the computer, but he suspects it would be a lot
tougher to hoodwink the human expert.

A human, for example, might detect changes in writing style in a ransom
note designed to disguise the identity of the writer, but still pick up
individualistic features that would point to the true author.

"One could use all kinds of approaches to overcome the disguise issue,"
he says.

Srihari found the research quite convincing, and it is being published
in the July issue of the Journal of Forensic Sciences. It won't convince
everyone, of course, because some still regard handwriting analysis as
akin to astrology. And some will have ample reason to challenge the
results. A criminal case could hinge upon the determination of whether a
defendant really penned that ransom note, so lawyers will have much to
fight about.

But so far, the findings have held up well.

"There have been a couple of federal court cases where the decision went
in favor of admitting handwriting evidence" after hearing his report,
Srihari says.

Maybe this is the guy we need to sic on the spammers. Surely his
computer program could find out who they are, give us their home
addresses, and put a few of them in jail.

------------------------ Yahoo! Groups Sponsor ---------------------~-->
The FREE Server Security Guide shows you how:  • DEPLOY THE LATEST ENCRYPTION and authentication techniques • DELIVER TRANSPARENT PROTECTION with the strongest security
without disrupting users. And more. Get your FREE Guide now:
http://us.click.yahoo.com/4tQ9vC/KyKEAA/Zr0HAA/kgFolB/TM
---------------------------------------------------------------------~->

------------------
http://all.net/ 

Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
Next message: Fred Cohen: "[iwar] [fc:Heads-Up.To.Ashcroft.Proves.Threat.Was.Known.Before.9/11]"
Previous message: Fred Cohen: "[iwar] Stupid Things People Do"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]
This archive was generated by hypermail 2.1.2 : 2003-08-24 02:46:32 PDT