Histograms of Oriented Gradients-Based Gesture to Voice Conversion System for Indian Sign Language using Raspberry Pi

Abstract

The hand gesture is one of the typical methods used in sign language. It is often very difficult for hearing-impaired people to communicate with the world. This paper presents a solution that will not only automatically recognize the hand gestures but will also convert it into speech and text output so that an impaired person can easily communicate with normal people. The system consists of a camera attached to a computer that will take images of hand gestures, histogram of gradient feature extraction is used to recognize the hand gestures of the person. Based on the recognized hand gestures, the system will produce voice output. The goal of this work is to develop a new type of human-computer interaction system to overcome the problems that users have been facing with the current system. A simple web camera is used to capture hand gesture images and recognize alphabets characters (A–Z) and numerals (0–9) using histograms of oriented gradients (HOG) features. The purpose is to implement the algorithm of extracting HOG features and these features are classified using a support vector machine (SVM) classifier for identification of Indian sign language (ISL). Hardware is developed using Raspberry Pi and Python programming.