Problems in Making OCR of Gurumukhi Script Newspapers

Main Article Content

Rupinderpal Kaur
Manish Kumar Jindal

Abstract

Newspapers are vital source of information. As a
historian had quoted “headline once in a lifetimeâ€. We
should do efforts to store such important information. Many
OCRs have been developed to recognize text on printed
documents on international and national level. But a few
efforts have been done to recognizing text of newspaper
articles especially in Gurumukhi script. To recognize text of
newspaper, two main stages are performed. First is to
segment newspaper article into various blocks and further
segmentation of blocks into smallest recognizable unit.
Second stage is to recognize the text. In this paper we had
discussed the various problems that we could face in both of
stages while developing the OCR for Gurumukhi script
newspaper articles.

Downloads

Download data is not yet available.

Article Details

Section
Articles