Facebook Improves Automatic Alt Text for Visually Impaired Users, Now Recognises Over 1,200 Concepts
Facebook’s Automatic Alt Text (AAT) system will be able to identify 10 times more concepts than earlier. By Tanishka Sodhi | Updated: 20 January 2021 14:54 IST
Photo Credit: Facebook
Highlights
AAT can identify types of animals, landmarks, activities, and more
It will include information about the relative size of elements
Facebook s Automatic Alt Text (AAT) system can now detect and identify 10 times more objects and concepts than it could when it was first launched, announced the company. Descriptions will also be more detailed, and AAT will be able to identify activities, landmarks, types of animals, and more. Facebook announced improvements to AAT, a system introduced by the company in 2016 that uses object recognition to generate descriptions of photos on Facebook and Instagram for visually impaired individuals.
Facebook в десять раз улучшил ИИ, который генерирует описание фото для слабовидящих
3dnews.ru - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from 3dnews.ru Daily Mail and Mail on Sunday newspapers.
CNN: Трамп помилует своего экс-советника Бэннона
ria.ru - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from ria.ru Daily Mail and Mail on Sunday newspapers.
Facebook improves alt text photo descriptions for blind, visually impaired users
The feature can now recognize landmarks, activities and types of animals. Listen - 01:46
Facebook is providing more detailed image descriptions for blind and visually impaired users. Andrew Hoyle/CNET
Facebook on Tuesday rolled out an update to its Automatic Alt Text (AAT) feature that improves the detail of photo descriptions for blind and visually impaired users. The tool, which launched in 2016, uses computer vision technology to automatically create descriptions. Updates are available when using a screen reader, an assistive technology that converts text to speech.
An example of a detailed image description for a photo of five people playing musical instruments.