Sistem Pengenalan Pola Huruf Braille Berbasis Audio Menggunakan Metode Naïve Bayes

Abstract

Blind people currently have limitations in developing their knowledge. The limitation is due to blind people still using braille character in interacting. Thus, the information received by blind people is slower than the general public. To overcome this problem, we propose a braille character pattern recognition system. There are several steps to recognize the braille character, as follows the digital image processing and pattern recognition using the naïve Bayes method. In the digital image processing step, there are several processes, such as the image acquisition process, enhancement, filtering, segmentation, and feature extraction. In the pattern recognition phase, the naive bayes method is used to predict the results of recognizable braille character patterns. The pattern recognition result is then converted into audio form using a raspberry pi device. Based on the results of our evaluation, the system is outperformed to recognize braille character with an accuracy of 88.172% and the average response time of the device into audio form about 5 seconds.
Keywords: Blind People, Braille Character, Naïve Bayes