Urdu Character Recognition using Neural Network

International Journal of Computer Trends and Technology (IJCTT)          
© 2016 by IJCTT Journal
Volume-36 Number-4
Year of Publication : 2016
Authors : Nighat Naaz Ansari, Ajay Kumar Singh


Nighat Naaz Ansari, Ajay Kumar Singh "Urdu Character Recognition using Neural Network". International Journal of Computer Trends and Technology (IJCTT) V36(4):172-175 June 2016. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
In this paper, recognition of the isolated Urdu characters is proposed. Method used for the recognition of Urdu characters is based on artificial neural network. In this method, first the image of Urdu alphabets is taken as input, then preprocessing steps such as conversion to Gray-scale image and later to binary image, noise removal is done . Then each character in the input image is segmented. Segmentation is done on the basis of connected components. Then after segmentation, recognition of characters is done by the help of neural network. In the last step, a text file shows the Unicode of the recognised characters and then the characters are matched with these codes. Simulation of the project is done in MATLAB.

[1] D.B. Megherbi, S.M. Lodhi, A..J. Boulenouar, “Fuzzy Logic Model Based Technique with The Application to Urdu Character Recognition”, Proceedings of the SPIE Application of Artifcial Neural Network in Image Processing v3962, pp. 13–24, 2000.
[2] Ankur Rana, Gurpreet Singh Lehal, “Offline Urdu OCR using Ligature Based Segmentation of Nastaliq Script”, International Journal of Sciemce and Technology (IJST) Doi:10.17485/ijst/2015/v8i35/86807.
[3] S.A. Husain., "A Multi-tier Holistic Approach for Urdu Nastaliq Recognition", Proceedings of the 6th International Conference on Multi-topic IEEE Conference (INMIC‟02), pp.528-532, 2002.
[4] J.A. Mahar, G.Q. Memon, S.H. Danwar, “Algorithm for Sindhi Word Segmentation using Lexicon Driven Approach”, International Journal of Academic Research (IJAR), vol. 28, 2011
[5] H. Malik ,M.A .Fahiem,”Segmentation of PrintedUrdu Script using Structural Features”, Proceedings of the 2nd International Conference in Visualisation (VIZ‟09), pp 191-195, 2009.
[6] S.T. Javed, S. Hussain, A. Maqbool, S. Jamil, H. Moin,”Segmentation Free Nastalique Urdu OCR”, World Academy Of Science, Engineering and Technology.
[7] J. Cowell, F. Hussain., "A Fast Recognition Segmentation for Isolated Arabic Character", Proceedings of the 6th International Conference on Information Visualisation, London, UK, pp.650-654, 2002.
[8] S.M. Azam, Z.A. Mansoor, M. Sharif, "A Fast Recognition Isolated Character by Constructing Character Signature Database", Proceedings of the International Conference on Emerging Technologies (ICET‟06), pp.568-575, 2006.
[9] Z.A. Shah, "Ligature Based Optical Character Recognition of Urdu Nastaleeq Font", Proceedings of the 6th International Conference on Multi-topic IEEE Conference (INMIC‟02), pp.25-25, 2002.
[10] Z.Ahmad, J.K. Orakzai, I. Shamsher, “Urdu Compund Character Recognition Using Feed Forward Neural Network”, Proceedings of the 2nd International Conference on Computer Science and Information Technology (ICCST‟09), pp. 457-462 ,2009.
[11] Saeeda N, Khizar H, Muhammad Imran R, Mohammad Waqas A, Madani Sajjat, “The Optical Character recognition of Urdu-like cursive script”. Journal of Pattern Recognition., pp.1229–48, October 2013.
[12] Nighat Naaz Ansari, Ajay Kr. Singh, “License Plate Recognition Using Template Matching”, International Journal of Computer Trends and Technology (IJCTT), vol. 35, no. 4, pp.175–178, May 2016.

Urdu characters, neural network, Gray-scale image, binary image, segmentation, Unicode.