Using OCR translation during a session

You can use optical character recognition (OCR) to capture writing or numbers from an image or object. Using OCR translation, you can capture text and translate it to a variety of languages. Refer to this article for a list of supported languages. 

You can also save a transcript of the OCR with a case report.

NOTE: This feature is available in the SightCall Enterprise and Premium Editions.

Requirements

To use OCR translation, you need to initiate a session using a scenario that has this feature enabled. Contact your SightCall admin if you have questions.

Related articles

• OCR (optical character recognition)
• How to use OCR in a Visual Assistance Session (Video)

Using OCR translation

When you start a session with a user, the user needs to be in a Visual Support app or the No-App Experience.

To use OCR translation:

1. Start a session with a scenario that has OCR translation enabled.
2. Select the Start Select Text on the Remote panel. The text capture window activates.
3. Ask the guest to move the capture window on their device so the desired content is within the capture area.
   
4. Select Start OCR to capture the text or numbers.
   
5. The original characters appear in the top box (1) and the translation appears in the lower box (2). 
   
6. You can adjust the translation, if needed:
   1. 1. To change the input language selection, select a new language from the first drop-down box on the left.
      2. To change the output language, select a new language from the second drop-down box on the right.
      3. Select Translate if you change either one of the drop-down boxes.
         NOTE: The default language is set within scenario’s use case configurations by your admin.
7. Select Apply to save the image to the default location and save the translation to the case report.

If OCR and chat transcripts are enabled for the tenant, then the image and the OCR transcript are saved in the case report for the session.