Scholarlink

The deaf community in India relies heavily on the Indian Sign Language (ISL) as a means of communication. But because so few people are fluent in ISL, there is a communication gap between the hearing and deaf communities. The Indian Sign Language Translator (ISLT) in this paper employs MediaPipe and LSTM to convert Indian Sign Language (ISL) to text and back again. The suggested approach first uses MediaPipe to extract hand movements and facial emotions from movies of ISL signals. The LSTM model, which is trained using a sizable dataset of ISL signs and their related text labels, is then fed these characteristics. The input feature sequence is processed by the LSTM model, which also creates the matching text labels. A dataset of ISL signs and the text labels that go with them was gathered in order to train and test the proposed method. The outcomes demonstrate that the suggested approach performs extremely well when converting ISL signs to text and vice versa. It is useful for usage in real-life scenarios since it can recognize and translate many indications in succession. Overall, a bridge between the hearing and deaf communities in India can be created by the proposed Indian Sign Language Translator, enabling seamless inclusion and communication. By allowing them to interact with the hearing world more effectively, it has the potential to greatly raise the quality of life for the deaf people in India.

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

Long Short-Term Memory Models and Mediapipe Based Framework for Indian Sign Language Translator

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • K. Karthika,
  • R. Devi Priya,
  • S. Sathishkumar,
  • Raghu Ramamoorthy,
  • K. Radhika

摘要

The deaf community in India relies heavily on the Indian Sign Language (ISL) as a means of communication. But because so few people are fluent in ISL, there is a communication gap between the hearing and deaf communities. The Indian Sign Language Translator (ISLT) in this paper employs MediaPipe and LSTM to convert Indian Sign Language (ISL) to text and back again. The suggested approach first uses MediaPipe to extract hand movements and facial emotions from movies of ISL signals. The LSTM model, which is trained using a sizable dataset of ISL signs and their related text labels, is then fed these characteristics. The input feature sequence is processed by the LSTM model, which also creates the matching text labels. A dataset of ISL signs and the text labels that go with them was gathered in order to train and test the proposed method. The outcomes demonstrate that the suggested approach performs extremely well when converting ISL signs to text and vice versa. It is useful for usage in real-life scenarios since it can recognize and translate many indications in succession. Overall, a bridge between the hearing and deaf communities in India can be created by the proposed Indian Sign Language Translator, enabling seamless inclusion and communication. By allowing them to interact with the hearing world more effectively, it has the potential to greatly raise the quality of life for the deaf people in India.