Optical Character Recognition (OCR)

An Optical Character Recognition (OCR) system is an application that enables one to convert scanned paper documents into editable and searchable texts. The engine analyses the structure of the document image and divides the page into elements such as blocks of texts, tables and images. These blocks are used to identify character image patterns which are used to advance several hypotheses about the character possibilities. These hypotheses are used to produce different character, word and line level variations and associated probabilities. The set of probability hypotheses are then searched to find the most likely combination of characters, words and lines to produce a textual representation of the image.

Evaluation of OCR:

(As reported in Hocking, J. and Puttkammer, M.J., 2016, November. Optical character recognition for South African languages. In Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech), 2016 (pp. 1-5). IEEE.)