Scholarlink

As digital transformation rapidly alters many facets of everyday life, finding effective ways to connect physical gestures with digital interfaces has become increasingly important. In this context, this research presents a comprehensive approach to hand-sign detection using advanced image processing and deep learning algorithms. A novel pre-processing pipeline for accurate hand landmark detection is proposed, ensuring diverse and representative datasets. The hand-sign recognition model achieves a classification accuracy of 96%, leveraging innovative techniques for robust feature extraction and classification. The system demonstrates significant improvements in reliability and efficiency, with potential applications in sign language translation and accessibility technology. The research includes the integration of advanced image processing techniques and the optimization of deep learning algorithms to enhance detection performance. This approach demonstrates significant improvements in both the reliability and efficiency of hand-sign recognition systems, with potential applications in areas such as human–computer interaction, sign language translation, and accessibility technology.

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

Intelligent Sign Language Detection System with Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sarnav Saikia,
  • Subhrojit Saikia,
  • Monita Wahengbam

摘要

As digital transformation rapidly alters many facets of everyday life, finding effective ways to connect physical gestures with digital interfaces has become increasingly important. In this context, this research presents a comprehensive approach to hand-sign detection using advanced image processing and deep learning algorithms. A novel pre-processing pipeline for accurate hand landmark detection is proposed, ensuring diverse and representative datasets. The hand-sign recognition model achieves a classification accuracy of 96%, leveraging innovative techniques for robust feature extraction and classification. The system demonstrates significant improvements in reliability and efficiency, with potential applications in sign language translation and accessibility technology. The research includes the integration of advanced image processing techniques and the optimization of deep learning algorithms to enhance detection performance. This approach demonstrates significant improvements in both the reliability and efficiency of hand-sign recognition systems, with potential applications in areas such as human–computer interaction, sign language translation, and accessibility technology.