Here’s a new use for an old lab project.
While many books have already been digitized, sometimes the visually disabled can’t access them and sometimes a title might not be available at all. That’s where the FingerReader comes in.
The FingerReader is the latest project to come out of the MIT Media Lab. It combines a camera mounted in the white ring shown at right with OCR software running on a PC. The user merely points at the words they are trying to read and the FingerReader scans it, coverts the image to text, and says it aloud.
Here’s the Media Lab explaining the project:
The FingerReader is a wearable device that assists in reading printed text. It is a tool both for visually impaired people that require help with accessing printed text, as well as an aid for language translation. Wearers scan a text line with their finger and receive an audio feedback of the words and a haptic feedback of the layout: start and end of line, new line, and other cues. The FingerReader algorithm knows to detect and give feedback when the user veers away from the baseline of the text, and helps them maintain a straight scanning motion within the line.
As you can see in the video below, the prototype doesn’t work very well. Even though they’ve been working on similar projects for at least a couple years, it’s still slow and somewhat inaccurate (and in dire need of a better voice synthesizer).
There’s no plans as of yet to develop this into a commercial product, which is probably a good thing. It’s a rather clunky and expensive way to solve a problem few have, and I think developing similar tech based on a smartphone would be both more cost effective and more fucntional.
In fact, for the most part that tech already exists. iPhones and most Android smartphones already have the camera and TTS which would be needed for this project, and they’re pretty good too. All that is missing is an app to covert what the camera sees into text which could be spoken aloud.