A magazine where the digital world meets the real world.
On the web
- Home
- Browse by date
- Browse by topic
- Enter the maze
- Follow our blog
- Follow us on Twitter
- Resources for teachers
- Subscribe
In print
What is cs4fn?
- About us
- Contact us
- Partners
- Privacy and cookies
- Copyright and contributions
- Links to other fun sites
- Complete our questionnaire, give us feedback
Search:
Fingers feeling focus
People with visual impairments use interfaces to get online that don’t rely on sight. For example, instead of reading text printed on a screen, screen readers can turn text on a webpage into speech. That works OK, but sometimes the methods for images can be a bit indirect, like relying on wordy descriptions of what’s in a picture. But now researchers in the USA have come up with a way for people with visual impairment to get more out of images – they have a method for automatically turning photos of faces into raised pictures that people can feel with their fingers.
The computer program concerned, TactileFace, first needs a portrait photo. Once it detects where in the photo the face is, it sets about redrawing the various features. The tough bit is that people can’t feel as much detail with their fingers as they can see with eyes, so the raised portraits need to be simpler than the original photos. To do this the computer needs to know which important lines to keep, and which details it can discard. Luckily, it’s been trained to know the big landmarks of a face, like the eyes, nose and mouth. It can then detect line edges in the rest of the face, ending up with a face that’s got a reasonable amount of detail without being too much to handle.
Finally, the portrait goes to a printer, where it’s printed on to special paper that swells when it’s exposed to the heat of the print head. A person with a visual impairment can then feel the face to find out what a person looks like. The researchers tested their system with a range of people, and it works well – folk were good at locating facial features, could figure out the pose the picture was taken in, and could even pick out two different pictures of the same person from a group. Feels like they’ve found a good solution!