DESIGN AND IMPLEMENTATION OF PAKISTAN SIGN LANGUAGE TRANSLATOR MODEL FOR SPEECH IMPAIRED

Abstract

One of the primary areas that the public ward on is social correspondence. Language is, doubt, the best means to communicate and connect with one another, both vocally without a and nonverbally. Because non-deaf persons have poorer comprehension of sign languages, there is a constant communication gap between the deaf and non-deaf hearing communities. As a result, numerous strategies have been used to address this problem, including turning sign language to text or audio and vice versa. In recent years, research into the use of puters, artificial intelligence, and machine learning to detect and translate sign language interactive prototype that was created with com has evolved steadily. The suggested system is the use of a Deep Learning model that was trained on signals. We used SSD MobileNet model to train our an dataset of photos that included PSL dataset and achieved an accuracy of 80% a in detecting the gestures in real time.