Numerals Recognition for Urdu Script

Abstract

Optical Character Recognition is a difficult task due to complexities of the script and varying location of the character in the image. Characters of Urdu script based languages are even more difficult to recognize but they have not received much attention even when Urdu ranks sixth in top 10 most-spoken primary languages (181 million). The problem in numeral recognition in Urdu is the fact that curves and cusps of numerals vary from person to person. This paper presents two schemes for the recognition of numerals of Urdu in unconstrained environment. These two approaches are Feature Extraction & Correlation.

Keywords: Optical character recognition (OCR), magnetic character recognition (MCR), correlation of images, feature extraction, urdu numerals