Evaluating Techniques Used for Bidirectional Sign Language Translation: A Review of Literature

Abstract

Sign language is the means of communication used by speech and hearing-impaired people to communicate with normal people. Among normal people, sign language is not a common language and it takes a lot of time and effort to figure out the meaning of signs. Due to this, normal people rarely communicate with hearing-impaired people and this communication gap isolates the hearing impaired people from the normal world. To solve this problem, there is a need for a system for translating sign to text and text to sign to make the communication smooth. Different algorithms have been used such as Convolutional Neural Networks(CNN), Support Vector Machine(SVM) have been used for training the system. The aim of this paper is to examine various approaches to sign language recognition and determine which one is the most effective.