3D Sign language translator using optical flow

Abstract

Communication is required to interact and socialize. Generally, communication used verbal communication in spoken or written words. However several people are unable to communicate verbally, since they were deaf or mute. Non-verbal communication is the most effective communication used by the deaf and mute. This communication uses sign language in the form of hand and body gestures. Hand gestures identification is the method to identify the position pattern of the hand and the body in order to translate the meaning and the purpose. This communication is intended to make normal person understand regarding the sign language that conveyed by the deaf. Many difficiluties faced by normal person to understand the sign language. Therefore interpreter tool for sign language is required to translate into easy-understood verbal language. This research only includes sign language from hand and body gestures, in order to translates into characters. The configuration of hand gestures detection must be done to describes Indonesian Sign Language (BISINDO). The optical flow method has been used in this research in detecting hand and body movements. By using this method, 65% from 20 different word has been succeeded to identified.