Seeing AI is an app designed by Microsoft for the blind and visually impaired. The developers brought together the power of the cloud and AI to deliver an intelligent app designed to help users navigate. Point the phone’s camera, select a channel, and the user hears a description of what the AI has recognized around them.
With respect to document image capture there are two modes: Short Text and Document.
When in the Short Text mode the device camera automatically sees and converts text to speech. This is great for fast recognition and gives a quick understanding of the item in view.
Another channel selection is called Document, this mode provides audio guidance to capture a printed page, the app then recognizes the text along with its original formatting.
When in document mode, the app provides guidance until you have moved the phone camera to a position where all four corners of the document are in the view finder. Once all the borders of the page are in full view the app automatically takes a snapshot of the page.
Searching for the optimum position is not necessary when using a document scanning stand. Since the entire document is already in the view finder when using a scan stand the Seeing AI automatic border detection feature may not find the edges of the document.
The solution is to tap on the screen and the photo will be taken directly without waiting for the borders to be detected.
Use the upload button in the lower right corner to share the document via email or store it using a service like DropBox.
The convenience of using a stand along with the powerful and innovative Seeing AI app offers users an easier more productive way to read and store documents.