Sign Language Translator

Photo by Khush Agrawal

•Aimed at providing aid for speech-impaired people.
•Fabricated an easy-to-use, low-cost, and lightweight device in the form of a glove.

Abstract

Description Sign languages are languages that use the visual-manual modality to convey meaning. Sign languages are expressed through manual articulations in combination with non-manual elements. Sign languages are full-fledged natural languages with their own grammar and lexicon. Unlike acoustically conveyed sound patterns, sign language uses body language and manual communication to convey the thoughts of a person fluently. It is achieved by simultaneously combining hand shapes, orientation and movement of the hands, arms or body, and facial expressions. This way of communication is, however, limited to a group of people, which introduces a communication barrier. The need for an interpreter is essential to tackle this problem. A possible approach is using computer vision and machine learning techniques. This approach can, however, be costly and needs a bulky hardware setup or particular application installation. Also, it is subject to lighting conditions and perspective problems. We devised a cost-effective and easy-to-use glove that can overcome these limitations and act as an interpreter flawlessly.

Avatar
Khush Agrawal
Senior Year Undergraduate Student

Reinforcement Learning

Related