Overview

Original Research

ISOLATED AND CONTINUOUS HAND GESTURE RECOGNITION BASED ON DEEP LEARNING: A REVIEW

BARAA WASFI SALIM 1, and SUBHI R. M. ZEEBAREE 2.

Vol 17, No 11 ( 2022 )   |  DOI: 10.5281/zenodo.7353683   |   Author Affiliation: ITM Dept., Technical College of Administration, Duhok Polytechnic University, Duhok, Iraq 1; Energy Eng. Dept., Technical College of Engineering, Duhok Polytechnic University, Duhok, Iraq 2.   |   Licensing: CC 4.0   |   Pg no: 1323-1340   |   To cite: BARAA WASFI SALIM, and SUBHI R. M. ZEEBAREE. (2022). ISOLATED AND CONTINUOUS HAND GESTURE RECOGNITION BASED ON DEEP LEARNING: A REVIEW. 17(11), 1323–1340. https://doi.org/10.5281/zenodo.7353683   |   Published on: 24-11-2022

Abstract

Getting to know sign language is of great research importance as it affects the lives of deaf and mute people and societies in general. The rapid development of deep learning techniques presents new horizons in sign language recognition because it can give more accurate results and deal with large amounts of data. This paper provides an overview of sign language recognition systems that use deep learning as a basis. A review of recent studies in this field and the division of recognition systems into continuous and isolated and the algorithms used in both methods: Recurrent Neural Network (RNN) based method, Convolutional Neural Network (CNN), and Three-Dimensional Convolutional Neural Network (3D-CNN), in addition to the challenges in systems, Identify the signal, problems, and prospects.

Keywords

Deep learning; Recognition of sign language; isolated identification, Continuous identification, CNN, RNN, LSTM.