ARABIC BRAILLE RECOGNITION AND TRANSCRIPTION INTO VOICE AND TEXT

Abstract

The general aim of this project is to design and implement a fully functional Optical Arabic Braille Recognition system to recognize printed Braille cells and to transcript it to regular voice and text context. The specific aim of the project was divided into two stages, firstly to recognize Arabic Braille letter and transcript it into equivalent voice and text file. The second stage is to recognize Arabic Braille word and transcript it to the equivalent voice and text file. The work has been implemented using special method for recognition and developed under MATLAB environment through several stages including image capturing or scanning, image preprocessing, edging and filling the Braille dots using morphological operation on Braille dots, image filtering to remove non Braille dots, Braille cell and dot framing based on pixel coordinates, generating equivalent decimal Braille code based on binary to decimal conversion of activated dots , apply matching algorithm to Braille decimal codes, get equivalent voice and text file of matched Braille cell. The implemented method has been tested with full four spaced pages of scanned Braille documents written using standard Arabic Braille and it has accredited by Sudanese rehabilitation center for blinds in Sudan. Documents were scanned using a commercially available scanner type (HP Scan jet djf2200) with 200 dpi resolution. The processing was performed on a PC with an Intel core 2 duo CPU and 2GB RAM. The CPU time was taken for a single spaced page to be processed is averaged at around 32.6s with rate of 100% for letter recognition and transcription and rate of 100% for word recognition and transcription.