Planet Arduino

For people not familiar with American Sign Language (ASL), being able to recognize what certain hand motions and positions mean is a nearly impossible task. To make this process easier, Hackster.io user ayooluwa98 came up with the idea to integrate various motion, resistive, and touch sensors into a single glove that could convert these signals into understandable text and speech.

The system is based around a single Arduino Nano board, which is responsible for taking in sensor data and outputting the phrase that best matches the inputs. The orientation of the hand is ascertained by reading values from the X, Y, and Z axes of a single accelerometer and applying a small change based upon prior calibration. Meanwhile, resistive flex sensors spanning the length of each finger produce a different voltage level according to the bend’s extent.

At each iteration of the program’s main loop, a series of Boolean statements are evaluated to pick the phrase that best matches the current finger bends and hand orientation, and this data is then outputted via the UART pins to an attached Bluetooth® HC-05 module. The final component is a connected phone running a custom app that takes the incoming words from Bluetooth® and saves them for text-to-speech output when the button is pressed.

To see more about this project, you can read ayooluwa98’s write-up here on Hackster.io.

The post This glove translates sign language using an array of sensors appeared first on Arduino Blog.

According to the World Federation of the Deaf, there are around 70 million people worldwide whose first language is some kind of sign language. In the US, ASL (American Sign Language) speakers number from five hundred thousand to two million. If you go to Google translate, though, there’s no option for sign language.

[Alex Foley] and friends decided to do something about that. They were attending McHack (a hackathon at McGill University) and decided to convert speech into sign language. They thought they were prepared, but it turns out they had to work a few things out on the fly. (Isn’t that always the case?) But in the end, they prevailed, as you can see in the video below.

The heart of the project is a pair of 3D-printed hands. At first, they accidentally printed two left hands. They printed a right hand quickly, but they found out later they were missing one segment which they wound up carving out of wood. Fishing line formed tendons and there were enough servos to require two CPU boards to drive everything.

The speech recognition is from Nuance and if listen closely to the video, you’ll see they are signing “hello” and “goodbye.” We’ll have to take their word for it that the signing is correct and legible.

This reminded us of the sign language gloves from the Hackaday Prize. These hands probably won’t advance the state of the art in prosthetics, but that wasn’t what they were going for.

Thanks to [Butter] for the tip.