If you’re one of the many people who hate poking at the tiny virtual keys on smartphone keyboards, then you might like the experimental “airwriting” glove system created by a team of computer scientists at Germany’s Karlsruhe Institute of Technology. When the glove’s wearer draws letters in the air with their hand, the system can identify which letters are being drawn. Those letters are converted into digital text, which could then be input into an email, text message, or any other type of mobile app.
The glove is able to detect hand movements via integrated accelerometers and gyroscopes. That data is wirelessly transmitted to a computer, which starts by using pattern recognition software to determine if the movements are actually the result of airwriting, or if the user is simply doing something such as cooking.
UPGRADE TO NEW ATLAS PLUS
More than 1,500 New Atlas Plus subscribers directly support our journalism, and get access to our premium ad-free site and email newsletter. Join them for just US$19 a year.UPGRADE
Once it’s determined that letters are indeed being drawn, the computer then sets about identifying the individual letters. The program incorporates statistical models of the unique signal patterns for every letter in the alphabet, and can account for differences in individual writing styles. It can also recognize approximately 8,000 words (as long as they’re drawn in all-capital letters), along with complete sentences.
So far, the system has an error rate of 11 percent – that drops to three percent, however, once it picks up on a specific user’s style of airwriting.
Doctoral student Christoph Amma, who developed the technology, now hopes to miniaturize the sensors to the point that the glove could be replaced by something less impractical to everyday use, such as a wrist band. Alternatively, he also envisions the hardware being incorporated into a smartphone – in that way, a single hand-held device (the phone) could be used both to detect hand movements, and to process the data.
Airwriting technology could additionally be used to interface with mixed-reality devices such as Google Glass, claims Amma, eliminating the need for any extra device with a touchscreen or virtual keyboard.