Mobile Application Based Translation of Sign Language to Text Description in Kannada Language

Authors

DOI:

https://doi.org/10.3991/ijim.v12i2.8071

Keywords:

Gesture recognition, Image processing, Sign language, Video processing.

Abstract


Sign language is a main mode of communication for vocally disabled. This language use set of representation which is finger sign, expression or mixture of both to express their information among others. This system presents a novel approach for mobile application based translation of sign action analysis, recognition and generating a text description in Kannada language. Where it uses two important steps training and testing. In training set of 50 different domains of video samples are collected, each domain contains 5 samples and assign a class of words to each video sample and it will be store in database. Where in testing test sample under goes preprocessing using median filter, canny operator for edge detection, HOG for feature extraction. SVM takes input as a HOG features and predict the class label based on trained SVM model. Finally the text description will be generated in Kannada language. The average computation time is minimum and with acceptable recognition rate and validate the performance efficiency over the conventional model.

Author Biography

Ramesh M. Kagalkar, Research Scholar, VTU-RRC, Visvesvaraya Technological University Karnataka, India.

Department of Computer Engineering, Dr.D Y Patil School of Engg. and Technology,Lohaegaon,Pune,Maharashtra,India

Downloads

Published

2018-03-29

How to Cite

Kagalkar, R. M., & Gumaste, S. V. (2018). Mobile Application Based Translation of Sign Language to Text Description in Kannada Language. International Journal of Interactive Mobile Technologies (iJIM), 12(2), pp. 92–112. https://doi.org/10.3991/ijim.v12i2.8071

Issue

Section

Papers