Scholarlink

<p>The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language; therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST Dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate.</p>

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

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

  • 期刊论文

  • 发表日期：

    2025年1月7日

查看全文
  • Pranav,
  • Rahul Katarya

摘要

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language; therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST Dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate.