Fb to pack extra particulars into descriptions of images for blind, visually impaired individuals

Facebook has redesigned its automatic alt text experience, which provides detailed descriptions of images for people who are blind or visually impaired.

The social network introduced AAT in April 2016 and used artificial intelligence and object recognition to automatically create descriptions of photos when needed.

Instagram added AAT in November 2018.


AAT is available to users with screen readers, an assistive technology that converts text and other on-screen elements into speech.

Facebook wrote in a newsroom post on Tuesday: “When Facebook users scroll through their news feed, they find all kinds of content – articles, comments from friends, invitations to events, and. photos of course. Most people can instantly see what's in these pictures, whether it's their new grandchild, a boat on a river, or a grainy image of a band on stage. However, many users who are blind or visually impaired can experience these images as long as they are properly provided with alternate text. A screen reader can describe the content of these images with a synthetic voice and enable BVI users to understand images in their Facebook feed. "

The company's AAT technology can now recognize more than 1,200 objects and concepts, more than ten times the number when the tool was introduced in 2016. This means that more photos now have descriptions.

These descriptions are also more detailed as the updated technology can identify activities, animals, points of interest, and other details. As an example, Facebook offers: "Can be a selfie of two people outdoors, the Leaning Tower of Pisa."

The social network also made it possible to include information about the location and relative size of items in a photo by providing the following examples:

Instead of providing a photo description of "a picture may be of five people", it can now be stated that two people are in the center of the photo and three more people are towards the edges, meaning the two in the center are in focus stand .

Instead of describing a landscape as "can be a house and a mountain," Facebook can now highlight that the mountain is in the primary object based on how big it appears compared to the house at its base.

The social network stated that AAT is available for photos in groups, newsfeeds and profiles, as well as for open pictures in the detail view, where the picture is shown in full screen mode and the background is black.

Alternate text descriptions are written simply so that they can be translated into 45 different languages.

Facebook Facebook Facebook

Facebook said it asked users who depend on screen readers for feedback on the types of information they wanted to hear and when they wanted to hear it, and found that when pictures were from friends and family, they wanted more information, and less when they weren't.

The social network explained what happens when users opt for more detailed descriptions: “A panel is displayed that gives a more complete description of the contents of a photo, including a number of items in the photo, some of which may not be in the list Standard description was mentioned. Detailed descriptions also include simple position information – top / center / bottom or left / center / right – and a comparison of the relative importance of objects described as "primary", "secondary", or "minor". These words have been specially chosen to minimize ambiguity. Feedback on this feature during development has shown that using a word like "large" to describe an object can be confusing as it is unclear whether the reference is to its actual size or its size in relation to other objects in an object Image relates. Even a Chihuahua looks great when photographed up close. "

Continue reading

Comments are closed.