Machine translation system to convert Sinhala and English Braille documents into voice

Reading Braille documents are a time-consuming and labor-intensive task. A blind person should touch every Braille letter by his or her fingers. Therefore, high sensitivity in fingers and memorizing every Braille letters are key factors in Braille reading. Due to enhancement in technology, several Optical Character Recognition (OCR) systems have been introduced for different languages in different parts of the world. However, in Sri Lanka, there are no systems that extract Sinhala or English Braille characters using OCR and convert those Braille codes to sound output. The main purpose of the research is to create a system that extracts both Sinhala and English Braille segments from a given Braille document and makes the Braille content into voice. At the beginning Embossed Sinhala or English Braille image which took from webcam or a high-resolution phone will use for image processing techniques such as gray scaling, thresholding, erosion, and dilation. Erosion and gray scaling help to eliminate the noise and the noise-free image used to detect contour. After pre-processing, the image using an OpenCV library do the segmentation and character extraction. Braille character recognition has done by taking binary to decimal equivalent numbers. Before generating voice output, recognized Braille letters should convert to corresponding language letters (either Sinhala letter or English) and mapping English letters can directly generate English words but in Sinhala need an additional step called Unicode Mapping to generate a Sinhala word. When a Braille document is in high quality, the system will reach for 95 percent accuracy level and generally, results have around 85.30 percent success rate. This software provides many usability characteristics to increase simplicity when it's using OpenCV and related technologies. Even teachers can use this to improve their teaching terminologies and explain things more clearly in their lessons.