Real time sign language detection system using deep learning techniques

Abstract

Humans require communication in order to survive. It is a fundamental and effective method for communicating thoughts, feelings, and points of view. A greater number of babies are being born with hearing abnormalities, which puts them at a communication disadvantage with the rest of the world, according to data on physically challenged children during the last decade. People who are deaf or hard of hearing typically use sign languages to communicate. Hand gestures are used by Deaf or Mute persons to communicate; as a result, non-Deaf people have a hard time understanding their messages. Systems that can detect different signs and provide information to common people are thus necessary. To address this issue, we have developed an automated sign language detection system using deep learning, which helps deaf/mute people can communicate with normal people.

Two Dimensional Deep CNN Model for Vision-based Fingerspelling Recognition System

“…Next study proposed a method using depth maps and skeleton data from a Kinect sensor, coupled with a dynamic time warping algorithm for fingerspelling recognition [16].…”