Election fraud robs Americans of their voice in government and impacts political results across the nation, making it a significant concern for federal, state and municipal governments. Any irregularities or fraud rising out of or in connection with voter registration or voting can constitute election fraud. Since the most common form of identification used at the polls is a signature, many states and municipal governments are trying to ensure that their processes include signature authentication.

As mail-in voting gains popularity, the potential for fraud increases because of a lack of uniformity in authentication across all states.

Some jurisdictions, for instance, do not verify a voter's signature on absentee ballots against signatures provided on voter registration forms. Other states require that absentee ballots be notarized or signed in the presence of two witnesses.

A number of states allow some or all elections to be conducted entirely by mail. Oregon became the first state in the nation to conduct a presidential election entirely by mail in 2004. Oregon maintains a vigorous signature verification process for qualifying mail-in ballots and claims that these procedures are key to its success of voting by mail. A team of election workers verifies each signature against a signature on file for registered voters and passes any ballots for which signatures do not match on to the county election clerk.

Oregon's process illustrates that signature verification is still not automated in most counties throughout the United States. The weakness of manual processes is that election workers are not handwriting experts and cannot provide reliable fraud detection capabilities even after completing a signature identification course.

Historically, this has been the only possible answer since technology for automated signature verification did not offer an industrially mature solution on par with visual verification. Detecting skilled forgeries was especially challenging, as none of the existing technologies could offer anything close to visual verification results. Today however, technology can detect random and skilled forgeries with an accuracy that far surpasses visual verification.

In applications that deal with signed paper documents such as absentee ballots, only the document's static, two-dimensional image is available for verification. This poses a challenge considering that detection has to address not only random forgeries that were produced without knowing the shape of the original signature, but also skilled forgeries, or those generated by people imitating the original signature.

Signature verification software imitates the methods and approaches used by human forensic document examiners. They account for the missing important biometric data, such as speed, acceleration, deceleration and pen pressure, and produce highly accurate signature comparison results.

Signatures in question are compared to those on file to determine natural deviations in individual styles that the human eye often cannot detect. The software is able to compare signatures from a variety of sources such as voter registration cards, signature cards or signature snippets cut from any type of document.

Several county governments across the United States are already employing this technology. With about 3,200 counties, parishes or independent cities in the United States with similar needs, it is only a matter of time until the automated signature verification technology becomes more pervasive.


About the Author

Yuri Prizemin is with Parascript, (parascript.com) which processes more than 75 billion imaged documents per year.