Make social networks more accessible to people with disabilities - this is what Facebook and Instagram aim to do through the use of artificial intelligence. From now on, photos published on these platforms will be equipped with a better description that will help blind and visually impaired people.

Facebook first launched this initiative back in 2016. Using automatic alternative text (AAT), the social network had set up a system to help blind and visually impaired people perceive photos published on the platform.

Relying on artificial intelligence, screen reading software can offer a description of images through visual recognition. And the system is now greatly improved, Facebook announced on its blog: “The latest iteration of AAT represents multiple technological advances that improve the photo experience for our users.”

Descriptions are now more detailed and the system recognises up to 10 times more photo content than when it was launched. The software can now describe the position of people in a photo and recognise actions and locations more accurately: “Detailed descriptions also include simple positional information - top/middle/bottom or left/center/right - and a comparison of the relative prominence of objects, described as “primary”, “secondary”, or “minor”. These words were specifically chosen to minimise ambiguity.

Feedback on this feature during development showed that using a word like “big” to describe an object could be confusing because it’s unclear whether the reference is to its actual size or its size relative to other objects in an image. “Even a Chihuahua looks large if it’s photographed up close!,” Facebook explains in its post.

For users, photos of their loved ones will be more detailed while a shorter description will be adapted to other photos posted on the platform. According to Techcrunch, Facebook will offer simple descriptions so that they can be more easily translated into other languages for other countries when the system launches globally.

 - AFP Relaxnews