Sign language sensorial glove

Abstract

This project aims to develop a sensor glove which can process hand gestures and translate them into the corresponding alphabetical letter according to the American Sign Language (ASL). This will allow a deaf person to communicate using the sign language alphabet to convey a message without the need for the receiving end to be conversant in ASL. The glove integrates a number of sensors capable of capturing the degree of bending of each finger. Ten flex sensors were used for this project, two for each finger, given that their resistance changes in proportion to the bending of the sensor so that any bending of the fingers is detected. The glove also makes use of the BNO055 motion sensor to enable the system to distinguish between two letters which employ the same finger formation but a different orientation. The same sensor was also used to detect any linear acceleration caused by the signing of an arch which represents the repetition of a letter. The code is executed on the LilyPad microcontroller and translates the sensory data into the corresponding alphabet character which is output on the Arduino software console. The data transmission from the LilyPad to the host computer is handled by the HC-06 Bluetooth module, whilst power is provided by an armband mounted Li-Po battery, thus ensuring wireless operation. In order to test the system accuracy, the glove was used to display each of the twentysix letters for ten times. The glove was tested by two subjects achieving an accuracy of 93.8% and 88.5% respectively. Most of the inaccuracies can be attributed to slight movements of the flex sensors relative to the glove fabric resulting in variations in angle of bend even if the same letter is being signed.