Parametric method of decoding the Sign Language

Parametric method of decoding the Sign Language
Author(s):
Roopa S, Shreesha J.
Keywords:
Sign language; Gaussian model; parametric method.
Abstract
Communication is a vital part of human life and is a challenge for the people who are speech/hearing impaired ones. Across the world, there are many people who are speech/hearing impaired. In their day to day life, they are facing lot of problems to communicate with others. To understand them, one has to either learn their language i.e. sign language or finger language. The system proposed in this paper aims at tackling this difficulty to some extent. In this paper, a webcam is used to recognize the hand positions and sign made. The gesture captured via webcam is converted into text/speech output which makes people understand what exactly is being conveyed. In the proposed method, the hands are first detected using skin color. Skin samples of various persons including male, female and different races are collected and the distribution of the skin pixel samples is modeled as a Gaussian in Cb-Cr color plane. This parametric method of skin/non skin classification is more accurate compared to non-parametric method. Finally, recognition of sign is performed by template matching method. The algorithm used in this paper is implemented using MATLAB.
Article Details
Unique Paper ID: 144950 Publication Volume & Issue: Volume 4, Issue 6 Page(s): 217 - 221
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org