Optical Character recognition (OCR)

What is OCR?

Physical documents are scanned into image files (jpg, jpeg, etc.). OCR refers to the transformation of image documents to native text. There is no cognitive intelligence or NLP in OCR, simply character extraction.

Why is OCR important in the workplace?

OCR can save time and effort in producing machine readable versions (i.e. ASCII) of image files and document scans.

How does Taiger use OCR?

Taiger embeds an OCR layer into the Taiger Solution Suite when dealing with image files and document scans. The Taiger engine will then take the machine-encoded characters from OCR to extract the relevant knowledge from the documents.

Examples

  • Extracting text characters from ID card scans.
  • Digitizing business card images.