Sign-language recognition system uses Kinect to aid accessibility

Despite its age, the original Kinect is still showing its (quite frankly, impressive) power. According to the Inside Microsoft Research blog, Microsoft Research Asia and the Institute of Technology at the Chinese Academy of Sciences have teamed up with researchers to test how the Kinect could be used in sign-language recognition.

According to the post on the Inside Microsoft Research blog, technology built from Kinect for Windows has been shown to help those who use sign language as their primary communication language. This can allow better interaction with computers, much like speech recognition software. Check out the video showing this in action:

It has a translation mode that can translate sign language into text or speech. Currently, American Sign Language is the only one supported. However, there is the capacity for system to support other variants of sign language as well.

More from News & Analysis

What is the US HIRE Bill and why is India’s $250-billion IT sector worried? Is the internet dead? What's this theory that OpenAI's Sam Altman says might be true?

“From our point of view,” Chinese Academy of Sciences Professor Xilin Chen told the blog. “The most significant contribution is that the project demonstrates the possibility of sign-language recognition with readily available, low-cost 3-D and 2-D sensors.”

It uses a digital avatar, which in Communications Mode can allow a deaf person to communicate with a hearing person. The avatar can act out text input in sign language. The deaf person can, in turn, reply using sign language which is then converted into text.

The Kinect has shown off its capabilities many times over since it was launched. Curious developers have managed to use the Kinect in all sorts of innovative ways, such as in 3D modelling or even for medical research.