Microsoft Edge Can Now Generate Image Descriptions for Screen Readers

Posted on March 17, 2022 by Laurent Giret in Microsoft Edge, Web browsers, Windows with 4 Comments

Microsoft Edge is now capable of generating automatic images descriptions for users browsing the web with screen readers. The accessibility feature uses Azure Cognitive Services intelligence to generate alt text for web images that do not include it.

“When a screen reader finds an image without a label, that image can be automatically processed by machine learning algorithms to describe the image in words and capture any text it contains. The algorithms are not perfect, and the quality of the descriptions will vary, but for users of screen readers, having some description for an image is often better than no context at all,” explained Travis Leithead, Senior Program Manager, Microsoft Edge.

According to Microsoft’s data, more than half of the images processed by screen readers are missing alt text, which is a big problem for making the Internet more accessible. If Microsoft Edge can now provide automatic image descriptions for screen readers, some unlabeled pictures won’t be sent to Microsoft for processing: The list of exceptions includes excessively small (icon size or smaller) and large images, decorative images, and everything that Microsoft’s Vision API recognizes as gory, sexually suggestive, or pornographic.


Auto-generated image labels can be turned on in the edge://settings/accessibility menu on Windows, macOS, and Linux, and users will also need to turn on Screen reader support on the Accessibility Internals page at edge://accessibility. Windows 10 and Windows 11 come with a built-in Narrator feature, but other screen readers are also compatible.

Microsoft is planning to improve this new accessibility feature over time thanks to image recognition and algorithm improvements. “We’re excited for our screen reader users to benefit from this new service and grateful for the opportunity to work to improve the web experience for all users,” Leithead said today.

Tagged with ,

Join the discussion!


Don't have a login but want to join the conversation? Become a Thurrott Premium or Basic User to participate

Comments (4)

4 responses to “Microsoft Edge Can Now Generate Image Descriptions for Screen Readers”

  1. Chris_Kez

    If Microsoft can get Edge to read ads to visually impaired users they can unlock even more value for shareholders! ?

  2. JH_Radio

    lol, let me tell you its not perfect. You can turn it on right from an immage too, it says something like no immage description available, go to the context menu to get a description.

    I turned it auto on from this menu .

    The good thing to me is that it only does this if there is no alt tag.

  3. hbko

    everything that Microsoft’s Vision API recognizes as gory, sexually suggestive, or pornographic”

    It’s troubling that Microsoft is choosing to play sensor for content. Do blind people not deserve access to pornographic or sexually suggestive content? A discussion over a Game of Thrones episode can easily trigger the gory images limit as well. What about a chat over shirtless Super Man?

    I know that in the US things are excessively controlled, blurred and beeped over so for some

    people this may seem

    natural… but building one culture’s values into the Vision API and enforcing them on everybody doesn’t feel right at all. It also feels like discrimination towards the visually impaired by outlining in advance the categories of content they should and shouldn’t be able to access.