Optical character recognition or OCR recognizes text within images, which enables you to gain further clarity on images and memes added on your Check workspace.

This article explains:

Supported languages include:

  • Arabic

  • Bengali

  • English

  • Filipino

  • French

  • German

  • Hindi

  • Indonesian

  • Malayalam

  • Marathi

  • Portuguese

  • Spanish

  • Telugu

How OCR works

Within each image item, you can view a snippet of the extracted text in the media panel.

Click ‘More’ to display the full extracted text.

Manually extracting text from images

For manually added images, click the ‘Extract text from image’ button.

Similarity matching between OCR extracted images and text items.

Once text extraction is done, text items that are similar to the image will be suggested.

In the illustration below, an image has been added on Check and the text has been extracted (1). A later text item bearing similar text is added to Check (2). The new text item will then be suggested as the image item (3).

Correspondingly, images with text added on Check after text items will be suggested as matches to the text items.

Learn more about similarity matching and suggestions

Extracted text search

There are various ways to search for image items using extracted text:

  • Regular search:

    • Click the gear icon to the right of the search bar and under items, select ‘Extracted text (OCR), then click update.

Input the text in the search box to display items matching it.

  • Similar item matching:

    • Open an item, click ‘Add similar’ and select any option from the dropdown list.

    • Paste (extracted) text into the search to reveal image items that match.

Did this answer your question?