Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Few-shot android malware classification with quantum-enhanced prototypical learning and drift detection.

Scientific reports·2026

Same author

HIRD-Net: An Explainable CNN-Based Framework with Attention Mechanism for Diabetic Retinopathy Diagnosis Using CLAHE-D-DoG Enhanced Fundus Images.

Life (Basel, Switzerland)·2025

Same author

Radiomics: Assessing Significance and Correlation with Ground-Truth Data in Precision Medicine in Lung Adenocarcinoma.

Bioengineering (Basel, Switzerland)·2025

Same author

Retraction notice to "Societal knowledge, attitude, and practices towards dengue and associated factors in epidemic-hit areas: Geoinformation assisted empirical evidence" [Heliyon 10 (2024) e23151].

Heliyon·2025

Same author

A Multi-Modal Approach for Exploring Sarcoma and Carcinoma Using FTIR and Polarimetric Analysis.

Microscopy research and technique·2025

Same author

Ex-vivo optical prognosis of fibroadenoma and grade ll & lll breast cancer.

Lasers in medical science·2025

Search research articles

Related Experiment Video

Updated: Sep 28, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Human-Computer Interaction with Hand Gesture Recognition Using ResNet and MobileNet.

Abeer Alnuaim¹, Mohammed Zakariah², Wesam Atef Hatamleh²

¹Department of Computer Science and Engineering, College of Applied Studies and Community Services King Saud University, P.O. Box 22459, Riyadh 11495, Saudi Arabia.

Computational Intelligence and Neuroscience

|April 5, 2022

Summary

This study developed an Arabic sign language recognition model using two CNNs, achieving 97% accuracy. The system enhances communication for the deaf community by classifying 32 Arabic alphabet signs.

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Sep 28, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Area of Science:

Computer Science
Artificial Intelligence
Human-Computer Interaction

Background:

Sign language is the primary communication method for deaf individuals, but variations exist globally, lacking standardization.
Arabic sign language, specifically, presents unique challenges due to its distinct nature and the absence of a unified classification system.
The ArSL2018 dataset, released in 2019, provides a foundation for developing automated Arabic sign language recognition systems.

Purpose of the Study:

To develop and evaluate a robust model for recognizing Arabic sign language alphabet signs.
To improve the accuracy and reliability of automated sign language classification systems.
To contribute to enhanced communication accessibility for the Arabic-speaking deaf community.

Main Methods:

A framework employing two Convolutional Neural Network (CNN) models, ResNet50 and MobileNetV2, was implemented.
Images were preprocessed by resizing to 64x64 pixels, converting grayscale to three-channel, and applying a median filter to reduce noise and prevent overfitting.
Ensemble learning combined the predictions of the individually trained ResNet50 and MobileNetV2 models to enhance overall performance.

Main Results:

The proposed framework achieved a high accuracy of approximately 97% on the ArSL2018 test dataset.
Preprocessing techniques, including image resizing, channel conversion, and median filtering, significantly improved model robustness.
The ensemble approach combining ResNet50 and MobileNetV2 demonstrated superior performance compared to individual models.

Conclusions:

The study successfully demonstrated a high-accuracy Arabic sign language recognition system through advanced deep learning techniques.
The implemented preprocessing and ensemble methods are effective in enhancing the robustness and performance of sign language classification models.
This research offers a promising step towards bridging communication gaps for the deaf community through technology.