The system includes a pair of gloves made with flexible and thin sensors along each of the fingers. The sensors detect hand movements and the way fingers are placed to signify individual letters, numbers, words and expressions.
These movements are converted into electrical signals that are sent to a printed circuit the size of a coin that is placed on the wrist. This printed circuit transmits these signals to a mobile phone in which an application translates them as words spoken at the rate of one per second.
The researchers also placed sensors with stickers on the face to capture facial expressions typical of the American sign language.
In the tests, they worked with four deaf people who use American sign language, who repeated each gesture of that language fifteen times.
A specifically created algorithm transformed these gestures into letters, numbers and words it represents, recognizing 660 gestures, including all the letters of the alphabet and the digits 0 to 9.