Israeli system gives virtual sight to the blind

OrCam is a smart camera mounted on the frames of your eyeglasses, which ‘sees’ text, recognizes objects and ‘whispers’ in your ear.

HAARETZ

A new, camera-based product from Israeli start-up OrCam gives the visually impaired the ability to both “read” easily and move around a lot more freely than they have been able to until now.

Reading aids for the visually impaired and the blind are typically cumbersome devices that recognize text in restricted environments or smartphone apps with limited capabilities.

The OrCam device, on the other hand, is a small camera that clips onto glasses and connects to a very powerful wearable computer. The device uses a bone-conduction speaker to read aloud the words or objects pointed to by the user, according to Gizmag..

By just pointing a finger, the user can get OrCam to understand what information is needed, whether it’s a newspaper article, a bus number or if it’s safe to cross the road. Even faces and places are continuously scanned and recognized. OrCam will tell the user when it sees a face or a place that is stored in its memory, without the user having to do anything.

An item can be stored in its memory by merely holding up that object and shaking it. Likewise, for a place or face just a “wave of your hand” launches the interface to store that image in OrCam’s memory banks.

The system currently recognizes English-language text and beginning this week will be sold through the company’s Web site for $2,500, about the cost of a midrange hearing aid. It is the only product of the privately held company so far.

OrCam was founded several years ago by Amnon Shashua, a computer science professor at Hebrew University of Jerusalem. It is based on computer vision algorithms that he pioneered with another faculty member, Shai Shalev-Shwartz, and one of his former graduate students, Yonatan Wexler.

“What is remarkable is that the device learns from the user to recognize a new product,” said Tomaso Poggio, a computer scientist at M.I.T. who is a computer vision expert and with whom Dr. Shashua studied as a graduate student. “This is more complex than it appears, and, as an expert, I find it really impressive.”