Hi-tech app
Israeli researchers develop way to verify signatures
A team of researchers has developed a smartwatch application capable of verifying handwritten signatures by gathering data from a person’s wrist movement during the signing process.
The new software, which was the outcome of a collaboration between researchers at Ben-Gurion University of the Negev and Tel Aviv University, uses motion sensors already found in smart wristband devices popularly worn today.
Using data compiled by the device’s accelerometer and gyroscope sensors, the app is able to sense changes in rotational motion and orientation, thereby training a machine-learning algorithm to distinguish between genuine and forged signatures, the researchers said.
“We based our hypothesis on the assumption that people adopt a specific signing pattern that is unique and very difficult for others to imitate, and that this uniqueness can be captured adequately using the motion sensors of a hand-worn device,” said Ben Nassi, a graduate student in Ben-Gurion University’s department of software and information systems engineering.
Nassi worked on the project alongside Prof. Yuval Elovici, director of Ben-Gurion University’s Cyber Security Research Center; Dr. Erez Shmueli of Tel Aviv University’s department of industrial engineering; and Alona Levy, a graduate student in Shmueli’s department.
As part of their research, the team asked 66 Tel Aviv University students to wear a smartwatch on their writing hand and then use a digital pen to record 15 samples of their genuine signature. Afterward, each student also traced other people’s genuine signatures and were asked to forge five of them.
“The results for both random and skilled forgery tests were encouraging and confirmed that our system is able to successfully distinguish between genuine and forged signatures with a high degree of accuracy,” Nassi said.
To date, online signature verification technologies have typically relied on dedicated digital devices, such as tablets or smart pens, to capture, analyze and verify signatures, the researchers said. Although several recent studies have looked at using other types of motion data to determine identity, the team stressed that its study is unique in its approach. “Using a wrist-worn device or fitness tracker provides more comprehensive data than other wearable devices since it measures the gestures of a user’s arm, hand and all fingers rather than just a single finger or the forearm,” Nassi said. Shmueli also pointed out that their method does not require a designated ad-hoc device in order to capture an individual signature. “You can use virtually any hand-worn device to write and collect the signature itself on a paper document, such as a contract, receipt or other non-digitized document,” he said. “Then, our system operates like an online verification system to comprehensively capture the dynamics of the signing process and confirm authenticity.” The researchers have filed for a patent for their initial system and are considering numerous options going forward. They plan to expand their research to include larger-scale experimentation, and investigate the benefits of collecting data from both a smartwatch device and a writing digitizer, such as a tablet, to see if combining information from both sources will improve accuracy. In addition, they said that they intend to study the impact of data extracted from additional sensors, such as those used in lie detector machines to measure heart rate variability. When asked how the software might be available commercially, Nassi said that the team was still figuring out which path it would like to take. “One direction that we are considering is to integrate it as part of a bank’s application,” he said. “Another direction that we are considering is to launch a startup that will verify a signature as a service so that it will be available for personal use.” While smart watches have not yet achieved the popularity of smartphones, Nassi said that surveys from the year 2015 already show that about one in five people use such a wristband. “The forecasts are that by 2020, a very large part of population that uses the Internet will own either a smartwatch or a fitness tracker,” he added.