Microsoft Edge Is Doing the Automatic Image Description Thing Now

The closest I’ve gotten to using Microsoft Edge is the rare occasion when Windows opens a webpage in it instead of my default Firefox. I hit just enough keystrokes to close it, then I go on about my business. This isn’t so much because I have a hate on for Microsoft (I did make the decision that I’m a Windows guy rather than a Mac guy), but simply because I wasn’t looking for a new browser, especially not one that couldn’t be used by screen readers upon release.

It’s come a long way since then, so I hear. I wouldn’t know that firsthand, obviously. But Carin sometimes has to use it for work and she says it’s not bad. As the only person I know of who does anything with it, I’ll take her word for it. Besides, she’s Carin. She generally knows what she’s talking about.

Anyway, if I ever do decide to use Edge for some reason, that reason might be this.

Microsoft Edge can now send unlabeled images to its Azure computer vision API for processing, which is governed by Microsoft’s privacy promises. The vision API creates alt text in English, Spanish, Japanese, Portuguese, or Chinese Simplified which can then be deciphered by screen readers. Microsoft Edge won’t attempt to add automatic labels to images that are smaller than 50 x 50 pixels, very large image files, images that are marked as decorative, or images that the Vision API categorizes as pornographic, gory, or sexually suggestive.
Microsoft is rolling out this new feature immediately in Microsoft Edge for Windows, Mac, and Linux, but it won’t be available in Edge on Android or iOS yet. You can try the new feature out by enabling “Get image descriptions from Microsoft for screen readers” in edge://settings/accessibility, and using Narrator or another screen reader to browse the web.

Microsoft says that there are already improvements in mind for the feature, like trying to determine if the alt text that someone was nice enough to include just isn’t very good and then improving on it. Well, you’re certainly going to have a plenty big enough dataset to work with there, Microsoft.

It’ll be interesting to see if Edge’s version of this is better than Chrome’s, which I’ve found to be extremely hit and miss during my admittedly brief brushes with it.

Leave a comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.