Gesture to Speech Conversion

Abstract

Sign language is a primary mode of communication for people with language disabilities. This language uses a set of representation that is a sign of finger, expression or mixture of both to express their information among others. This system presents a new approach for translation based on mobile application of analysis of sign, recognition and generation of a textual description in Kannada language. We use two important steps of training and testing. In training, 50 different domains of video samples are collected, each domain contains 5 samples and assigns a class of words to each video sample and will be stored in the database. During the test, the sample is pre-processed using a median filter, a smart operator for edge detection, HOG (Histogram Oriented Gradients) is used for the extraction of features. SVM (Support Vector Machine) takes the input as a HOG feature and predicts the class label based on the trained SVM model. Finally, in the Kannada language, the text description will be produced. The average calculation time is minimal and with an acceptable recognition rate and validates the performance efficiency compared to the conventional model.