Audio/Text Aided System Using Sign Language

Abstract

This paper presents an intelligent system allowing handicapped aphasiacs to perform basic communication tasks. It has the following features:A 2-sensor data measures the hand gestures of a patient in terms of the bending degrees of his hands,A hand language recognition subsystem recognizes language components from the hand gestures. It employs multiple regression analysis to automatically extract proper hand features so that the recognition model can be fast and correctly constructed by a radial basis function neural network,A coordinate-indexed virtual keyboard allows the users to directly access the letters on the keyboard at a practical speed. The system serves as a viable tool for natural and affordable communication for handicapped aphasiacs through continuous hand language input.