Hand Gestures to Speech Translator Tool for Impaired People |
Author(s): |
Jameer S Jamadar , Raghavendra R Maggavi |
Keywords: |
Hand Gesture, Sign Language, Web camera |
Abstract |
Sign language is the most significant methodology that is used for communication between hearing and speech impaired people to the normal people present in the rest of the world. Generally the people who cannot talk, they uses sign language as a communication medium. They always find difficulty in communicating with others who don’t known sign language. The aim of this project is to remove this barrier and to help these impaired people for their better communication. This project is based on the necessity of developing a software tool that can convert sign language into speech. This will help in communication taking place between the mute societies with the other over-all public. In this project, web camera is used for capturing the hand gesture performed by the impaired people which converts the hand gesture to an image. Mute people can perform different hand gesture and that will be transformed into speech so that normal people can understand their manifestation. Sign language is the language used by dumb people and it is a communication ability that uses signs instead of sound to deliver meaning instantaneously. In our project different Hand shapes, orientations and movement of the fingers forms a different signs and that is expressed fluidly in a speech. Signs are used to converse words and sentences to viewers. A various hand gestures made in a sign language, are particular movements of the hands with a specific shapes made by fingers. A sign language typically delivers sign for complete words. It also provides signs for different letters to make words that don’t have equivalent sign in the sign language library. And also different numbers can be indicated by different signs of hand and fingers. In this project matlab software plays the major role, a camera is used to capture the hand gesture and it is processed into the matlab software and after processing equivalent audible sound is given at output. Different resolution camera can be used for better results. It is better to use a 3 to 5 megapixel camera because if we use lower resolution camera then it will create a distorted image that cannot be recognised easily, and if we use very high resolution camera then it produced a large size image that will take more time to process. So we are in process of evolving a prototype using this method to ease the communication between dumb people and normal people. |
Other Details |
Paper ID: IJSRDV3I50213 Published in: Volume : 3, Issue : 5 Publication Date: 01/08/2015 Page(s): 297-300 |
Article Preview |
|
|