Site icon COOL BLIND TECH

Artificial Intelligence and Text Recognition unite in Microsoft’s Seeing Ai iPhone App

Cool Blind Tech logo

Not a month has gone by since We posted an article on Narrator including AI-driven image tags and Microsoft is back at it yet again, though with an older project which finally has made public fruition. Introduced at Build 2016, this project had a goal of bringing powerful image recognition technology which could be used to augment every day life, especially when combined with the power of the cloud.

Today, The app is available in the iOS app store in the United States, Canada, India, Hong Kong, New Zealand and Singapore, for free.

In a post to the Microsoft Accessibility blog, Microsoft explains it in this fashion .

The app uses artificial intelligence and the camera on your iPhone to perform a number of useful functions.

  • Reading documents, including spoken hints to capture all corners of a document so that you capture the full page. It then recognizes the structure of the document, such as headings, paragraphs and lists, allowing you to rapidly skip through the document using voiceover.
  • Identifying a product based on its barcode. Move the phone’s camera over the product; beeps indicate how close the barcode is – the faster the beeps, the closer you are – until the full barcode is detected. It then snaps a photo and reads the name of the product.
  • Recognizing people based on their face, and providing a description of their visual appearance, such as their gender, facial expression and other identifying characteristics.
  • Recognizing images within other apps – just tap Share, and Recognize with Seeing AI.

In our experience, the app is able to even read computer screens in the short-text channel mode, and does so instantly as you move your arm towards and away from text. Reading coupons in a newspaper is more intuitive than having to wait for a picture to be snapped, and bar codes are often recognized in under 30 seconds thanks to the way it guides the user to it. Face recognition works well and can be taught to recall faces of loved ones after you take 3 pictures of them. Easily, this app rivals more expensive solutions and will become a must-have tool within any vision-impaired iOS user’s arsenal. The incredible power of Seeing AI lies in not just the cloud, but also at being able to perform this recognition offline and in real-time. Turning airplane mode on during a page scan still kept up with scrolling printed text, however features such as bar code and face/scene detection will require one.

Join Jessica to understand just how intuitive the app really is in this podcast and see for yourself what Seeing AI can do, as not even ten thousand words could give it full justification. She walks through the app, from the quick start guide to the various channels in great detail.

The official tutorials for the app, comprised of 9 videos, can be found at this link of a YouTube playlist.

Exit mobile version