Gesture Based Vocalizer for Deaf & Dumb

Gesture Based Vocalizer for Deaf & Dumb

A. Ravindra P Rajput, Professor, Department of Electronics & Communication Engineering, UBDTCE,

 B. Amith Kumar K S, Student, Department of MTECH (DCN), UBDTCE

Abstract– We proposed the Gesture based vocalizer for Deaf & Dumb. Gesture Vocalizer is a social cause project. The survey found that hearing-impaired people found it very difficult to communicate with others. Hearing-impaired people usually speak with hand gestures, and it is difficult for other people to understand sign language. It implements a gesture-based vocalizer that can recognize all hearing-impaired gestures, convert them to voice, and display them on the LCD screen. Basically, the data glove contains two types of sensors: a flex sensor and an accelerometer as a tilt sensor. Wireless data gloves are used. This is a standard cross glove with flexible sensors along the length of each finger and thumb. Dumb can use gloves to perform hand gestures, which are converted into voice so that others can understand their expression. This system helps dumb people communicate with others. A wearable glove controller is designed with flex sensors attached on each finger, which allows the system to sense the finger movements, and an accelerometer, which are used to sense the hand movement of the disabled person. The wearable input glove controller sends the collected input signal to the system for processing. The system uses Random forest algorithm to predict the correct output to an accuracy of 95% on current training model.

Index Terms—Flex Sensor, Arduino Nano, HC-05, Gesture Detection, Arduino Bluetooth Text to Speech Converter