• ISSN: 2349-6002
  • UGC Approved Journal No 47859

Sign Language Encoder-Decoder

  • Unique Paper ID: 159083
  • Volume: 9
  • Issue: 11
  • PageNo: 353-357
  • Abstract:
  • Sign Language is a visual language that requires manual manner to communicate what an individual wants to convey. Sign Language consists of its own grammar and lexicon. It is used by dumb and deaf people to portray what they want to say. It acts as a basic mode of communication for people with hearing impairment and speaking impairment, without which communication between them and normal individuals might be difficult. We focus on the development of an automated software system to convert speech to sign language, sign language to text so that the deaf people can effectively communicate among themselves as well as with other people. Creating a desktop application that makes use of a computer’s webcam to capture an individual marking gestures for American sign language (ASL), and interpret it into corresponding text and speech in real time. To enable the detection of gestures, we are making use of a LSTM Neural Network (RNN). A RNN is highly efficient in tackling computer vision problems and is capable of detecting the desired features with a high degree of accuracy upon sufficient training. This Web application will not only help deaf people to understand what a person is trying to ask to them instead it will help a normal person as well, to collaborate and to understand a deaf person.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 9
  • Issue: 11
  • PageNo: 353-357

Sign Language Encoder-Decoder

Related Articles