get_transformation_ocr: Encode OCR error to a string.

In sdglinkage: Synthetic Data Generation for Linkage Methods Development

Description

get_transformation_ocr randomly assign a Optical Character Recognition (OCR) error to a string. This function was converted from the Python code in Febrl ( developed by Agus Pudjijono in 2008, refers to reference https://link.springer.com/chapter/10.1007/978-3-642-01307-2_47.

Usage

get_transformation_ocr(string)

Arguments

string

A string.

Value

It returns the string with a randomly assgined OCR error following rules extracted in the ocr_rules dataset. It also comes with the change log of the transformation.

Examples

get_transformation_ocr('how are you?')

sdglinkage documentation built on April 27, 2020, 5:09 p.m.