Facebook‘s latest artificial intelligence experiment aims to make the social network a lot friendlier to the visually impaired.
Starting Tuesday, the company will roll out a feature called “automatic alternative text” to users on its iPhone app. The technology will describe images to people who are blind or visually impaired by interpreting what’s in a picture using artificial intelligence software that recognizes faces and objects.
Users with a visual impairment using screen reader technology will hear a list of items the software detects in a picture.
For example, if the picture were a selfie showing two people wearing sunglasses on a beach, the audio description would say, “Image may contain: Two people, smiling, sun glasses, sky, outdoor, water.”
The iPhone’s built-in screen reader, VoiceOver, must be turned on for Facebook’s photo descriptions to be read. VoiceOver is a part of Apple’s accessibility features, which allows the phone to speak what is written on the screen. The feature is widely used by those with visual impairments.
“With more than 39 million people who are blind, and over 246 million who have a severe visual impairment, many people may feel excluded from the conversation around photos on Facebook,” read Facebook’s blog.
“Before today, people using screen readers would only hear the name of the person who shared the photo, followed by the term “photo” when they came upon an image in News Feed. Now we can offer a richer description of what’s in a photo thanks to automatic alt text.”
But Facebook is still experimenting with how the tool works.
Initially, photo descriptions will only be available in English; but the company hopes to broaden the vocabulary as the tool is developed.
For now descriptions will be confined to a vocabulary of 100 words so the user isn’t overwhelmed with details. For instance, the automated voice may only tell a user that a photo features three people smiling outdoors without adding that the trio also has drinks in their hands. Or it may say the photo is of pizza without adding that there’s pepperoni and olives on top of it.
Facebook also has to be careful with the technology, as things could easily go wrong. Google learned this the hard way after an image recognition feature in its Photos app labeled a black couple as gorillas, prompting the company to issue an apology.
Eventually, Facebook hopes to refine the technology so it provides more precise descriptions and even answers questions that a user might pose about a picture.
Facebook also plans to turn on the technology for its Android app and make it available through web browsers visiting its site.
– With files from The Associated Press