Skip to main content
Docs
Go to the Studio
Roberty Studio
RPAImage Recognition

Simple OCR

Simple OCR

Performs character recognition (OCR) on an image and returns the text identified. Ideal for extracting textual information from screenshots or document images.


Options​

Image path to be identified​

Enter the full path of the image file that will be analyzed by the OCR. The image must contain the text you want to extract.

Select the language​

Select the language of the text present in the image: Portuguese - Brazil or English - USA.

Returns​

Javascript code​

js
actions["action-id"].text // text recognized in the image (Text)

Field selection​

  • text — text recognized in the image (Text)

Rules and Conditions​

  • The Image path to be identified field is required.
  • You can also provide a PDF file; in that case, only the first page is converted to an image and analyzed.
  • Images with good resolution and contrast between the text and the background give better results.
  • For recognizing documents with a more complex structure (tables, forms), use the Advanced OCR action.
  • The text returned may contain small inaccuracies depending on the image quality.