OCR (Optical Character Recognition)

Description

OCR (Optical Character Recognition) is the technology of converting handwritten, typewritten, or printed text in images or scanned documents into a computer readable text format that can be searched or manipulated with a word processor or other similar means. The potential of OCR systems is enormous because they enable users to harness the power of computers to access printed and scanned documents, allowing searches that once required hours or days to be accomplished in seconds.

Automate Desktop's OCR action provides new opportunities and techniques with regards to combining OCR capabilities in an automated environment. It enables you to convert handwritten, typewritten, or printed text, as well as text contained in images, to an Automate Desktop variable or dataset, making it possible to search for a word or phrase, store text more compactly, and apply techniques such as text mining or text-to-speech.

Available activities

Select the corresponding link for more details regarding each activity:

Activity	Description
OCR - Get text	Retrieves text from an image or PDF file and populates a variable with the results.
OCR - Get word(s)	Retrieves one or more words from an image or PDF file and then creates and populates a dataset with the results.
OCR - Get line(s)	Retrieves one or more lines of text from an image or PDF file and then creates and populates a dataset with the results.