Recognition System of Indonesia Sign Language based on Sensor and Artificial Neural Network

Abstract

Sign language as a kind of gestures is one of the most natural ways of communication for most people in deaf community. The aim of the sign language recognition is to provide a translation for sign gestures into meaningful text or speech so that communication between deaf and hearing society can easily be made. In this research, the Indonesian sign language recognition system based on flex sensors and an accelerometer is developed. This recognition system uses a sensory glove to capture data. The sensor data that are processed into feature vector are the 5-fingers bending and the palm acceleration when performing the sign language. The most important part of the recognition system is a feature extraction. In this research, histogram is used as feature extraction. The extracted features are used as data training and data testing for Adaptive Neighborhood based Modified Backpropagation (ANMBP). The system is implemented and tested using a data set of 1000 samples of 50 Indonesia sign, 20 samples for each sign. Among these 500 data were used as the training data, and the remaining 500 data were used as the testing data. The system obtains the recognition rate of 91.60% in offline mode.