Skip to main navigation Skip to search Skip to main content

Arabic Sign Language Recognition Using Deep Machine Learning

  • Prince Mohammad Bin Fahd University
  • King Fahd University of Petroleum and Minerals

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

22 Scopus citations

Abstract

In this work, we present an effective method for automatic Arabic Sign Language recognition that uses a Convolutional Neural Network (CNN) for feature extraction and a Long Short-Term Memory (LSTM) for classification. AlexNet, a CNN architecture, is used to extract deep features from the input image while the LSTM is used to preserve the sequential structure of the video frames. The method was tested on a data set consisting of 50 repetitions of 150 signs commonly used in daily activities performed by three signers. The proposed method achieved an overall recognition accuracy of 95.9% for the signer-dependent case, and 43.62% for the more difficult signer-independent case.

Original languageEnglish
Title of host publication2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665437738
DOIs
StatePublished - 2021
Externally publishedYes
Event4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021 - Alkhobar, Saudi Arabia
Duration: 6 Dec 20218 Dec 2021

Publication series

Name2021 4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021

Conference

Conference4th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2021
Country/TerritorySaudi Arabia
CityAlkhobar
Period6/12/218/12/21

Keywords

  • Arabic sign language recognition
  • CNN
  • LSTM

Fingerprint

Dive into the research topics of 'Arabic Sign Language Recognition Using Deep Machine Learning'. Together they form a unique fingerprint.

Cite this