Sign and speak glove

This wire covered glove is capable of turning your hand gestures to speech, and it does so wirelessly. The wide range of sensors include nine flex sensors, four contact sensors, and an accelerometer. The flex sensors do most of the work, monitoring the alignment of the wearer’s finger joints. The contact sensors augment the flex sensor data, helping to differentiate between letters that have similar finger positions. The accelerometer is responsible for decoding movements that go along with the hand positions. They combine to detect all of the letters in the American Sign Language alphabet.

An ATmega644 monitors all of the sensors, and pushes data out through a wireless transmitter. MATLAB is responsible for collecting the data which is coming in over the wireless link. It saves it for later analysis using a Java program. Once the motions have been decoded into letters, they are assembled into sentences and fed into a text-to-speech program.

You’ve probably already guess that there’s a demo video after the break.

Continue reading “Sign and speak glove”

Building a flex sensor from component packing materials

Hacks like this one don’t help us recover from extreme pack-rat behavior. Driving home the point that one should never throw anything away [Peter] built a flex sensor from component packing material. It uses the black conductive foam in which integrated circuits are sometimes embedded for shipping. Above you can see the grey rectangle which is the sensor itself. in the background of the image, each component used in the build is labelled except for the tape.

The project starts with the foam being cut to the appropriate size and thickness. He does the same with some aluminum foil, then rips tape strips to act as the enclosure. Fine wire from some cable shielding serves as the two conductors for the sensor. He attaches each wire to an upturned piece of tape, followed by the foil, and finally the foam. When the two halves are assembled in the video after the break, [Peter] hooks up his multimeter to show the change in resistance as the sensor is bent.

We think it will take a clever calibration algorithm to get this working reliably, but it’s no more troublesome than the optical flex sensors we saw in this links post. Continue reading “Building a flex sensor from component packing materials”

Wireless MIDI piano glove

Sometimes you just don’t have space for a baby grand. [Abdullah] got around this problem and built a virtual wireless MIDI piano. Unlike it’s inspiration, it’s not bad but we still love it.

[Abdullah] got his hands on some flex sensors and attached them to a glove. These resistive sensors are put through a voltage divider and sent to a microcontroller (a PIC16F778, we believe) and corresponding MIDI notes are chosen. These MIDI notes are sent to a computer and played over a speaker.

Right now, only a single arpeggio is coded into the microcontroller. Depending on which finger is bent shifts this arpeggio up and down the keyboard. That being said, the firmware can be easily modified to recognize standard piano fingering so chords can be played. The only issue is moving the hand up and down the keyboard.

[Abdullah] is planning on making his glove completely wireless with a microcontroller and battery sewn into the glove. Here’s to hoping he’ll keep us posted.

Check out [Abdullah]’s demo after the break.

Continue reading “Wireless MIDI piano glove”

Building optical flex sensors

[Joel] dug up this hack that he pulled off over ten years ago. It’s inspired by the Nintendo PowerGlove, and uses flex sensors to react to movements of your fingers. The interesting thing is, he built these optical flex sensors himself.

He likes to say that this is a ghetto fiber-optic setup. The inlaid diagram above gives you an idea of how the sensors work. An IR LED and infrared diode are positioned at either end of a piece of clear aquarium tubing. When the tube is flexed, the amount of light that makes it to the diode is diminished, a change that can be measured by a microcontroller. [Joel] found that he could increase the resolution of the sensor by adding something to the center of the tube, blocking the light when not straight. In this case he used pieces of scrap wire. The outside of the sensor was also wrapped in shrink tubing to keep ambient light from interfering with measurements.

He uses a trimpot to tune the sensors but we wonder how hard it would be to add a calibration algorithm to the firmware?

Electric mountain board with glove control

Last summer, we saw [Andres Guzman]’s electric mountain board tearing around the University of Illinois campus. He’s back again, only this time the board isn’t controlled with a PlayStation controller. [Andres] built a wireless glove to control his mountain board.

An Arduino and power supply is mounted to the glove. A 2.4GHz transceiver serves as the comm link between the glove and board. The speed control is handled by this flex sensor from Sparkfun. With the flex sensor held between the middle and ring fingers, all [Andres] needs to do to apply power is slightly bend his fingers.

There’s also a number of safety features built into the board. To enable power to the boards motor, there’s a dead man switch on the glove underneath the thumb. If [Andres] were to take a nasty spill, he would release the switch and the board would come to a stop. [Andres] also made sure the board would shut down if the wireless link was interrupted. The build seems pretty safe, even if he is tearing around his campus in the video below.

Continue reading “Electric mountain board with glove control”

SudoGlove gets a big software upgrade

[Jeremy Blum] recently finished writing a couple of software packages for his SudoGlove system that turns it into a music controller with a lot of features. We’ve seen the hardware in a previous post and as a goal for this iteration he decided not to alter the hardware or the firmware controlling it whatsoever–making this a PC-side software only hack. It’s nice to see improvement on the original ideas as we feel most of the glove-based projects we’ve covered end up getting thrown in the junk box after the developer’s interest wanes.

After the break you can see and hear a demonstration of the complete system. The front end of application shown was written using Processing and includes a slew of user configurations for each sensor on the glove itself. Under the hood [Jeremy] built on the PureData framework in order to really unlock the potential for translating physical movement into synthesized sound. There is also a visual feedback application which will help you practice your movements, important if you’re giving live performances where each finger is a different instrument. Everything for this project, both hardware and software, has been released under a CC license so check out [Jeremy’s] site if you’re interested in building on part or all of the good work he’s done.

Update: [Jeremy] wrote in with a bit of a correction for our synopsis. The application shown in the video is written entirely in PureData and the visual debugger was written with Processing. The two are standalone packages that don’t depend on each other. He also sent us a link to download the code packages.

Continue reading “SudoGlove gets a big software upgrade”

From sign language to spoken language

As part of a senior design project for a biomedical engineering class [Kendall Lowrey] worked in a team to develop a device that translates American Sign Language into spoken English. Wanting to eclipse glove-based devices that came before them, the team set out to move away from strictly spelling words, to combining sign with common gesture. The project is based around an Arduino Mega and is limited to the alphabet and about ten words because of the initial programming space restraints. When the five flex sensors and three accelerometer values register an at-rest state for two seconds the device takes a reading and looks up the most likely word or letter in a table. It then outputs that to a voicebox shield to translate the words or letters into phonetic sounds.