Software uses smartwatch motion data for signature verification

Researchers have developed software that leverages a smartwatch’s motion detection capabilities to verify a handwritten signature, according to a report by New Atlas.

In a new paper, researchers from Tel Aviv University (TAU) and Ben-Gurion University of the Negev detail how the software uses motion data collected by a smartwatch as the wearer jots down their autograph to confirm its authenticity.

The motion data captured by the smartwatch’s accelerometer or gyroscope serves as a unique identifier that determines whether the signature is genuine or a falsification, the researchers said.

“Using a wrist-worn device such as a smartwatch or a fitness tracker bears obvious advantages over other wearable devices, since it measures the gestures of the entire wrist rather than a single finger or an arm,” said study co-author Dr. Erez Shmueli of TAU’s Department of Industrial Engineering. “While several other recent studies have examined the option of using motion data to identify users, this is its first application to verify handwritten signatures – still a requirement at the bank, the post office, your human resources department, etc.”

In an effort to test the software’s accuracy, the researchers outfitted 66 TAU undergraduate students with smartwatches and asked them to write their signature 15 times on a tablet using a digital stylus.

The researchers then showed the students a video of various individuals signing their autograph and asked the students to forge five of the signatures. The participants were given sufficient time to practice their forgings as well as the promise of a reward for “exceptional forgeries.”

The verification software were successful in achieving “extremely high level” of accuracy in detecting forgeries, the researchers said.

However, the one flaw of the authentication method is that the majority of people (66 percent) wear a watch on their non-dominant hand, according to a recent survey cited by the researchers.

This means that most people would need to switch the smartwatch to their dominant hand when writing their signature.

Despite this, the researchers have applied for a patent with plans to eventually bring the technology to market. In the meantime, the team said they are working on improving the software.

“Next we plan to compare our approach with existing state-of-the-art methods for offline and online signature verification,” Dr. Shmueli said. “We would also like to investigate the option of combining data extracted from the wearable device with data collected from a tablet device to achieve even higher verification accuracy.”

Article Topics

biometrics  |  biometrics research  |  gesture recognition  |  signature verification