Facebook's AI provides enhanced photo descriptions for the visually impaired

Facebook has been using AI to describe photos for the visually impaired for some time now. Now, the social media platform seems to be ramping up its efforts, with a new version of its Automatic Alternative Text (AAT) technology to better utilise object recognition to generate description of images on demand.

Facebook detailed the improvements in a blog post, suggesting that the new AAT has been improving 10 times since it was introduced back in 2016 to recognise over 1,200 concepts. According to the social media platform, the latest iteration of AAT “represents multiple technological advances that improve the photo experience for our users.”

The blog noted, “Descriptions are also more detailed, with the ability to identify activities, landmarks, types of animals, and so forth — for example, “Maybe a selfie of 2 people, outdoors, the Leaning Tower of Pisa.” It can now identify activities, landmarks, types of animals, and so forth. For example, a photo might read, “Maybe a selfie of 2 people, outdoors, the Leaning Tower of Pisa.”

The new object detection system can also recognise the number of people and where they are in the frame. Beyond offering a simple summary of the photo’s content, users will now be able to choose a detailed description that outlines the size, position, and nature of objects. The latest improvements to AAT signify a big leap for accessibility on the social network for the visually impaired.