Microsoft’s AI will describe images for the blind users

Artificial learning is the current hot property in the corporate world. From Facebook to Apple to Google, every tech company is employing machine learning to make their products more productive and user-friendly.

This technology becomes all the more relevant and impactful when the users are people with disabilities because AI gives them a new means to explore hitherto untouched domains. Something similar is happening in Redmond presently where Microsoft is working on a feature for Office apps like Microsoft Word and PowerPoint that will automatically suggest image and slide deck captions, called alt-text, using AI algorithms.

This means when those files are presented to blind users, computer tools designed to translate the information onscreen into audio have text descriptions to work with.

Microsoft is arraying its Computer Vision Cognitive Service to achieve this feat that uses neural networks trained with deep learning techniques to better understand and describe the contents of images. This helps the AI better understand and describe the contents of images so that the suggestions for Alt-Text are on point.

“We will offer you automatic suggestions for alt-text when you insert a photographic image that can be recognised with high confidence,” writes the Office 365 team in a blog post. “Through machine learning, this service will keep improving as more people use it, saving you significant time to make media-rich presentations accessible.”

The service will be rolling out for Word and PowerPoint users on PC starting next year but would be limited to Office 365 subscribers only. The company is also releasing additional templates for Office that are so structured so as to “ensure ease of navigation with a screen reader and keyboard”. The fonts and colours deployed here are easy to read with low vision or colour blindness as well.