Scholarlink

The presented research paper presents a thorough study and enhancement of Sign Language Recognition Systems (SLRS) using Artificial Intelligence (AI) and Machine Learning techniques. Sign language is an important part in communication for the Deaf and mute community, however existing systems face difficulties with accuracy and accessibility. Our study introduces an innovative approach to enhance the effectiveness and efficacy of sign language gesture detection by using neural networks with LSTM and Dense Layers concepts. The proposed system shows significant advancements, including hyper-accuracy, faster training times, and a simplified architecture compared to traditional deep neural network models. These improvements solve essential communication barriers for the Deaf and mute community, offering promising solutions for sign language recognition in real-time.

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

Real-Time Sign Language Recognition Using Deep Learning Algorithms LSTM Neural Networks and MediaPipe Holistic

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Shrishail Patil,
  • Ritesh Sah,
  • Mrunali Rajkule,
  • Akshada Bagul,
  • Swaliha Attar

摘要

The presented research paper presents a thorough study and enhancement of Sign Language Recognition Systems (SLRS) using Artificial Intelligence (AI) and Machine Learning techniques. Sign language is an important part in communication for the Deaf and mute community, however existing systems face difficulties with accuracy and accessibility. Our study introduces an innovative approach to enhance the effectiveness and efficacy of sign language gesture detection by using neural networks with LSTM and Dense Layers concepts. The proposed system shows significant advancements, including hyper-accuracy, faster training times, and a simplified architecture compared to traditional deep neural network models. These improvements solve essential communication barriers for the Deaf and mute community, offering promising solutions for sign language recognition in real-time.