Urdu Qaeda: Recognition System for Isolated Urdu Characters
Nabeel Shahzad, Brandon Paulson, Tracy Hammond · 2009
This paper presents an online system for recognizing isolated, hand-sketched Urdu characters drawn on a Tablet PC. Attributes of Urdu characters are analyzed to define a set of features which are then trained and classified using a weighted, linear classifier. As a proof of concept, we have integrated our recognition algorithm into an application used to help people learn the Urdu language. Preliminary results obtained from our studies showed an accuracy of 92.8% for native Urdu writers. Author Keywords