Articles in this section

See more

OCR (optical character recognition)

  • Updated
Follow

In order to use the OCR functionalities during a call, they need to be activated for that specific usecase, see here for an overview of that process: https://support.sightcall.com/hc/en-us/articles/360041518652

 

The Agent can capture text from an image using the OCR (Optical Character Recognition) feature.  

First, the Agent must start the OCR functionality by clicking on the “Select text” button: blobid0.png

This brings up a selection window, like below: 

blobid1.png

Anything within the centre white-lined box will be available for OCR. 

Once the Guest has centred the image to be OCR’d within the white-lined box, they click the “OCR” button: blobid2.png

Which will bring up the image OCR’d in a separate window to be saved:  

blobid3.png

And also show the results of the OCR function in the console: 

blobid4.png

The Agent can copy the OCR’d text to the clipboard by pressing the “Copy to clipboard” option. If the Agent clicks “Apply”, this will save the OCR’d text as part of the case report, accessible via the Admin Portal. 

If you would like to see a video demonstration of this feature, you can click here: https://support.sightcall.com/hc/en-us/articles/360041141792-How-to-use-OCR-in-a-Visual-Assistance-Session-Video-

 

Related articles