Augmented reality glasses ‘translate foreign menus as you read’

Glasses that can automatically translate foreign menus into the wearer’s own language have been unveiled in Japan.

The next-generation spectacles were revealed at a gadget fair on the outskirts of Tokyo and could be available in time for the city’s hosting of the Olympics in 2020.

An engineer for NTT Docomo demonstrates a headset which can translate foreign-language menus

An engineer for NTT Docomo demonstrates a headset which can translate foreign-language menus

By using augmented reality the glasses can project text in the wearer’s native tongue over unfamiliar signs and menus, potentially proving invaluable for British tourists whose grasp of Japanese is limited.

The invention may be particularly useful for those who journey beyond the most popular destinations in Japan where foreign-language menus are rarely found.

In a statement Japanese telecoms firm NTT Docomo, the company behind the glasses, said: “Character recognition technology enables instant language translation for users travelling abroad and reading restaurant menus and other documents.”

Another function the smart glasses can perform is turning any flat surface into a touchscreen with the wearer using a finger ring to activate animated tags.

(Fonte: Telegraph)

Microsoft Research uses Kinect to translate between spoken and sign languages in real time

Microsoft’s Kinect is a wonderful piece of technology that seems to know no bounds. Microsoft Research is now using it to bridge the gap between folks who don’t speak the same language, whether they can hear or not.

[sz-youtube url=”″ caption=”Kinect captures the gestures” /]

As you can see in the video below, the Kinect Sign Language Translator is a research prototype that can translate sign language into spoken language and vice versa. The best part? It does it all in real time.

In short, Kinect captures the gestures, while machine learning and pattern recognition programming help interpret the meaning. The system is capable of capturing a given conversation from both sides: a deaf person who is showing signs and a person who is speaking. Visual signs are converted to written and spoken translation rendered in real-time while spoken words are turned into accurate visual signs.

While this is clearly a massive achievement, there is still a huge amount of work ahead. It currently takes five people to establish the recognition patterns for just one word. So far, only 300 Chinese sign language words have been added out of a total of 4,000.

Guobin Wu, the program manager of the Kinect Sign Language Translator project, explains that recognition is by far the most challenging part of the project. After trying data gloves and webcams, however, the Kinect was picked as the clear winner.

Wu says there are more than 20 million people in China who are hard of hearing, and an estimated 360 million such people around the world. As a result, this project could be a huge boom for millions around the globe, if it ever makes it out of the lab.


fonte The Next Web