Scholarlink

Arabic Sign Language (ArSL) recognition systems are essential tools for promoting inclusivity by facilitating communication between the Deaf community and individuals unfamiliar with sign language. By enabling effective communication, these systems can significantly enhance information accessibility and improve the daily experiences of Deaf individuals. In this project, we present an ArSL recognition approach using the KArSL database and an advanced model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. Our model achieved over 85% accuracy, demonstrating its competitive performance and potential compared to other methodologies tested on this dataset. This high accuracy underscores the model’s effectiveness in recognizing Arabic sign language signs and highlights the value of using deep learning techniques to bridge communication gaps within the Arabic-speaking Deaf community.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Arabic Sign Language Classification Using CNN-LSTM Integration for Enhanced Gesture Recognition

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ihssane Bouhanou,
  • Noureddine Aboutabit

摘要

Arabic Sign Language (ArSL) recognition systems are essential tools for promoting inclusivity by facilitating communication between the Deaf community and individuals unfamiliar with sign language. By enabling effective communication, these systems can significantly enhance information accessibility and improve the daily experiences of Deaf individuals. In this project, we present an ArSL recognition approach using the KArSL database and an advanced model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. Our model achieved over 85% accuracy, demonstrating its competitive performance and potential compared to other methodologies tested on this dataset. This high accuracy underscores the model’s effectiveness in recognizing Arabic sign language signs and highlights the value of using deep learning techniques to bridge communication gaps within the Arabic-speaking Deaf community.