American Sign Language Translation via Smart Wearable Glove Technology

Abstract

In the world of sound, for those without it, sign language is a powerful tool to make their voices heard. The ASL, short for American Sign Language is the most widely used sign language across the globe with certain variations according to the country. In this work, we developed a wearable wireless gesture decoder module that can translate the fundamental set of ASL gestures into corresponding alphabets and words. Our project utilizes a glove that houses a series of flex sensors on the metacarpal and inter-phalangeal joints of the fingers to detect the bending of fingers, through piezoresistive effect. The glove is outfitted with an accelerometer as well, that helps to detect the hand movements. Simple classification algorithms from machine learning are then applied to translate the gestures into alphabets or words. With the assistance of a bluetooth module, the data is sent wirelessly. The result is then displayed and heard on the android smartphone using an android application named “Dastaana”, which is an Urdu word for glove. Portability, compactness, cost-effectiveness and a user-friendly android application gives this system an edge.