By Yuri Prizemin, Parascript

Election fraud robs Americans of their voice in government and greatly impacts political results across the nation, making it a significant concern for federal, state, and municipal governments. Any irregularities or fraud arising 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 making a conscious effort to ensure that their processes include signature authentication.

Mail-in voting is proving to be an increasingly popular method of voting in the United States. The potential for fraud is greatest in this area 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, including Colorado, Arizona, Oregon and Washington, 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. The state maintains a vigorous signature verification process for qualifying mail-in ballots and claims these procedures are key to its success with 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 the files on record, to the county election clerk.

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

Nonetheless, this was the only possible answer since technology for automated signature verification did not offer an industrially mature solution that was at least 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 technology can detect random and skilled forgeries with an accuracy that not only equals – but 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. In order to account for the missing important biometric data (such as speed, acceleration, deceleration, pen pressure, and others) and produce highly accurate signature comparison results, signature verification systems imitate the methods and approaches used by human forensic document examiners.

Automatic signature comparison is executed by a powerful combination of verifiers using seven fundamentally different approaches. In particular, they combine a human-like holistic analysis of a signature and signature segmentation with a subsequent analysis of the signature elements. The whole verification process can be described as “the workings” of a group of highly skilled experts. When they work together as a team, their areas of expertise complement each other, resulting in improved overall performance. Each of them focuses on the analysis of a certain range of informative signature features. These range from generic characteristics, like similarity of signature histogram and presence and number of typical elements, to detailed comparison of geometrical shapes of signature fragments or directions of trajectory sections. This approach

You do not have flash or javascript support.

Average (1 vote)

Reply