Optical Character Recognition

This post is an introduction to optical character recognition.

OCR Methods

Mahalanobis is a method to calculate the distance between multidimensional vectors, and it is used in OCR. It uses the concept of Mahalanobis distance.

OCR Software

This is a non-extensive list of OCR (Optical Character Recognition) software:

ABBYY FineReader
OnmyPage
Readiris
pytesseract

ABBYY FineReader

Developed by ABBYY (Russia).

Propietary and non-free

https://www.abbyy.com/en-eu/finereader

OmnyPage

Developed by Nuance (US).

Propietary and non-free.

https://www.nuance.com/print-capture-and-pdf-solutions/optical-character-recognition/omnipage.html

Readiris

Developed by I.R.I.S. (Belgium), a company from Canon group (Japan).

Proprietary and non-free

http://www.irislink.com/EN-ES/c1682/Readiris-16-for-Windows—OCR-Software.aspx

pytesseract

pytesseract is a FOSS Python library for OCR.