Use optical character recognition

Mediagraph Support
Mediagraph Support
  • Updated

Who can use this feature?

All members can see OCR content when enabled by an admin. Taggers and above can run OCR on previously uploaded content.

Available on all plans

Optical Character Recognition (OCR) is one of the most mature and valuable Artificial Intelligence features available. OCR enables Mediagraph to recognize and extract text from any uploaded image file. It can provide clues to the content of images, and can be useful for scans of articles, awards, and other ephemera. Making this information searchable can offer a massive improvement in content discoverability. All OCR text is added to the image's metadata in Mediagraph and is factored into the general search. In case of errors or inaccuracies, it is easy to edit OCR-generated text content.

OCR is a feature of Mediagraph's auto-tagging service. Auto-tagging must first be enabled in order to use OCR. Admins can learn how to enable auto-tagging here. Auto-tagging will be applied to all new uploads once it is enabled. If necessary, auto-tagging can be applied retroactively to a previous upload.

Submit a previous upload for OCR processing

  1. In the workspace, select any image(s) you would like to submit for OCR processing by clicking their thumbnails.
  2. Click on the gray sprocket to open the Action Menu.
  3. Select Run Auto Tagging from the menu. If auto-tagging has already been applied to all selected images, the menu item will be greyed out. If you do not see the menu item, ensure auto-tagging has been enabled.
  4. After a brief process, auto-tagging and OCR will be applied to the selected images. The progress bar at the top of the screen shows you when the process is complete. Follow the instructions below to view the OCR content.

View and edit OCR content for a new upload

  1. In the workspace, double click on an image to open the Asset Detail view.
  2. If auto-tagging was enabled prior to uploading the image, you will see a Text Content tab. Click to open it and view any OCR content found in the image.
  3. If there are errors you want to correct, click Edit at the bottom of the tab and make any necessary changes in the text field that opens.
  4. Click the blue Save button to apply your changes.


Was this article helpful?

0 out of 0 found this helpful

Have more questions? Submit a request