Abstract:
The complexity associated with Urdu fonts regarding OCR in newspapers is being dealt with active research. When creating an Urdu OCR you are limited to a certain font siz...Show MoreMetadata
Abstract:
The complexity associated with Urdu fonts regarding OCR in newspapers is being dealt with active research. When creating an Urdu OCR you are limited to a certain font size i.e. if working with a font size of 12, you will have to create a database covering all characters/words of font size 12. In order to work with another font size of same Urdu font you'll have to cover all the characters/words of that respective font size. The OCR technique should be generic where the font size should not matter. The objective was to create a technique that could be applied to any Urdu script font size, without worrying about the variation of characters/words caused by the disposal of ink in Urdu newspaper clippings. In this paper the authors have developed a technique using point feature matching on cropped Urdu newspaper clippings with font Jameel Noori Nastaleeq and converted them into editable textual Unicodes.
Date of Conference: 12-13 December 2015
Date Added to IEEE Xplore: 19 May 2016
ISBN Information: