From a contact lens that delivers tactile sensations to the cornea, to a 3D-printed ring that reads text aloud in real-time, advances in technology have opened up some groundbreaking ways for the visually-impaired to consume printed content. Researchers from Australia's Curtin University have now unveiled a low-cost reading device that processes graphical information, enabling the blind to digest documents such as bills, PDFs, graphs and bank statements.
"People who are blind are often blocked from certain career paths and educational opportunities where graphs or graphics play a strong role," says Dr Iain Murray, Senior Lecturer at Curtin University's Department of Electrical and Computing Engineering who developed the digital reading system with PhD student Azadeh Nazemi. "We hope this device will open up new opportunities for people with vision impairment."
The device measures 20 x 15 x 3 cm (7 x 6 x 1.1 in) and features a set of high contrast controls with tactile markings for navigation. Using pattern recognition, machine learning technologies and a range of segmentation methods, the system separates content into blocks of text and pictures that are arranged in the correct reading order.
These blocks are then identified as images, graphs, maths or text and extracted either though optical character recognition (OCR) or Mathspeak, a tool for verbalizing mathematical calculations. The information is then converted to audio format with navigation markup and can be translated into 120 different languages via the built-in speech engine. Audio instructions are also built into the device.
“Our system is easily operated by people of all ages and abilities and it is open source, meaning anyone with the skill can use and modify the software to suit their application,” Dr Murray said. He expects that the cost for the reading device will be as low as US$100 per unit, a price that could make it a very real solution for many, even in developing countries. He is now seeking philanthropic financing to get the device into production.
Source: Curtin University
Of course, visually - impaired young people need to be catered for, so children's materials could join in in developing the standard. (It would save a lot of processing if the digital file for a drawing had a simple code for types of animal rather than the software having to calculate that something is a lion, say, from all the other four-legged animals).
It is not a stretch of the imagination to see this technology potentially developed to accept video input, perhaps with an automatic pause for the information to be fully comprehended before continuing.