Signage Recognition Framework for Visually Impaired People

This paper presents a signage recognition framework for Malaysian Visually Impaired People (VIP). Independent navigation is always a challenge to visually impaired people whenever they attempt to find their way in a building (i.e. an office, a seminar room) and other amenities (i.e. an exit, ladies/gents toilets) even with a walking stick or a guide dog. The proposed framework will capture an image of a public signage and transform it into a text file using Otsu’s optical character recognition method. The text file will be read by a speech synthesizer that tells the visually impaired people what the image is. This framework does not require huge database of the signage but only the character database. The framework is being tested on 5 blind folded subjects to check on its performances. Experimental results yield a recognition rate of 86.0%. This proof of concept shows that signage recognition could be easily achieved using optical character recognition and voice synthesizer.