Video device could assist the visually impaired
[LIMA] A device that converts real-world images into pixels could improve the eyesight of visually impaired people who have been fitted with implants to partially restore their vision, suggests the first study to enhance the low resolution of retinal implants.
The device was developed by researchers at the University of Southern California, United States. The researchers say that pixelated vision could make tasks such as navigation, route planning and object finding easier for those with visual impairments.
- The head-mounted display turns images into pixelated ones that highlight key features
- Better image processing could improve vision in those with retinal implants
- Further technological and surgical advances are needed
In the study, published in the Journal of Neural Engineering this month (1 March), 19 healthy people were fitted with a head-mounted display. A video camera collected images from each subject's point of view, then these were converted into pixels and displayed on the headset screen in front of the subject.
The image-processing algorithms that produce the pixels also used intensity, saturation and edge-information from the camera's images to highlight the five most important, or salient, parts of the image.
Subjects performed three tasks: walking an obstacle course, finding objects on a table and searching for a particular target in a cluttered environment.
"At the moment, retinal implants are still low-resolution. We believe that our algorithm will enhance them by providing the user with more information when they are looking for a specific item," James Weiland, lead author and associate professor of ophthalmology and biomedical engineering at the university, tells SciDev.Net.
Research into retinal implants for people with irreversible eye diseases is ongoing. At the moment, the Argus II Retinal Prosthesis System, approved by the European Union two years ago and the United States last month, is the world's only approved device intended to restore some functional vision for people who are blind.
Weiland says that the implants enable people to "detect motion and large objects and have improved orientation when walking. In most cases, they can also read large letters."
Image-processing algorithms can be used to enhance implants' performance and provide greater confidence to patients when performing tasks, especially in a new environment, he adds.
The next step is to create a wearable computer to carry out the image processing, Weiland says.
He believes that smartphones and other devices for the blind and deaf have an important role to play in making technology more inclusive. He added that it does not always have to be complicated. "Low-cost tools to provide some assistance to the blind may involve a simple piece of software on a cell phone". This could be particularly useful in developing countries.
Weiland adds: "Braille phones are a possibility, but most phones already have an 'accessibility' mode that enables blind users to hear what icon they are touching, so much is already available".
Guillermo Reátegui, a specialist in eye diseases at the British-American Hospital in Lima, Peru, says: "This trial is part of much broader studies to try to enhance the vision of patients … and it opens a window for visually impaired patients requiring retinal implants. I think it is an important step forward, which must be accompanied by new technological — and even surgical — developments."
Link to abstract (the full paper can be accessed until the end of March by creating an account)
Journal of Neural Engineering doi:10.1088/17412–560/10/2/026017 (2013)