Urdu Nastaleeq Optical Character Recognition

This paper discusses the Urdu script characteristics, Urdu Nastaleeq and a simple but a novel and robust technique to recognize the printed Urdu script without a lexicon. Urdu being a family of Arabic script is cursive and complex script in its nature, the main complexity of Urdu compound/connected text is not its connections but the forms/shapes the characters change when it is placed at initial, middle or at the end of a word. The characters recognition technique presented here is using the inherited complexity of Urdu script to solve the problem. A word is scanned and analyzed for the level of its complexity, the point where the level of complexity changes is marked for a character, segmented and feeded to Neural Networks. A prototype of the system has been tested on Urdu text and currently achieves 93.4% accuracy on the average.

Authors:

• Zaheer Ahmad
• Jehanzeb Khan Orakzai
• Inam Shamsher
• Awais Adnan

Keywords:

• Cursive Script
• OCR
• Urdu.

References:

[1] U. Pal and Anirban Sarkar, "Recognition of Printed Urdu Script",
"Proceedings of the Seventh International Conference on Document
Analysis and Recognition (ICDAR 2003)".
[2] Raymond G. Gordon, "Ethnologue: Languages of the World Fifteenth
Edition" SIL International, 2005.
[3] Khalid Saeed, "New Approaches for Cursive Languages Recognition:
Machine and Hand Written Script and Texts".
[4] K. Saeed, Three-Agent System for Cursive Script Recognition, " Proc.
CVPRIP ÔÇÿ2000 Computer Vsion, Pattern Recognition and Image
Processing-5th Joint Conf. on Information Sciences, JCIS-200, Vol.2,
PP.244-247, Feb 27-March 3, N.Jersry 2000.
[5] K. Saeed, R Niedzielski, "Experiments on Thinning of Cursive-Style
Alphabets, "Inter Conf. on information Technologies ITESB -99, June
24-25, Minsk 1999.
[6] Inam shamsheer, Zaheer Ahmad, Jehanzeb Khan Orakzai, Awais
Adnan, "OCR For Printed Urdu Script Using Feed Forward Neural
Network," MLPR 2007 :International Conference on Machine Learning
and Pattern Recognition", 2007.