The goal of vision-based sign language
recognition is to improve communication for the hearing
impaired. However, the majority of the available sign
language datasets are constrained. Real-time hand sign
language identification is a problem in the world of
computer vision due to factors including hand occlusion,
rapid hand movement, and complicated backgrounds.
In this study, we develop a deep learning-based
architecture for effective sign language recognition using
Single Shot Detector (SSD), 2D Convolutional Neural
Network (2DCNN), 3D Convolutional Neural Network
(3DCNN), and Long Short-Term Memory (LSTM) from
Depth and RGB input films
Keywords :
Sign Language Recognition System, Multi Modal Approach, Skeleton Based.