Armband Controller Translates Sign Language Into Text

A gesture-controlled armband has been used to break down communication barriers for deaf people by converting sign language into written text.

Researchers from the Arizona State University developed the system—dubbed Sceptre—using two wrist worn Myo devices. Using software that can be run on a smartphone or computer, the armbands are able to decipher American Sign Language (ASL) gestures.

A video showing how the technology works was posted on YouTube by Prajwal Paudyal, one of the researchers involved in the project. Words and phrases like "all morning," "every night," "headache" and "upset stomach" are translated from Paudyal's gestures.

"Communication and collaboration between deaf people and hearing people is hindered by a lack of a common language," Paudyal wrote in the video's description. "Although there has been a lot of research in this domain, there is room for work towards a system that is ubiquitous, non-invasive, works in real-time and can be trained interactively by the user.

"This work demonstrates that the system is very easily trained using just one to three training instances each for 20 randomly chosen signs from the ASL dictionary and also for user-generated custom gestures."

Sceptre uses a classification system that takes input data from the accelerometer, gyroscope and electromyography (EMG) sensors found in the Myo wristband. The system is able to achieve an accuracy of 98 percent for ASL gestures.

Myo armbands have been used by developers to create a variety of functions, from controlling characters in video games, to replacing computer keyboards and mice with virtual, on-screen versions.