A New Technique for Segmentation of Handwritten Numerical Strings of Bangla Language

Full Text (PDF, 416KB), PP.38-43

Views: 0 Downloads: 0


Md. Aktaruzzaman 1,* Md. Farukuzzaman Khan 1 Ahsan-Ul-Ambia 1

1. Dept. of Computer Science and Engineering, Islamic University, Kushtia, Bangladesh

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2013.05.05

Received: 5 Aug. 2012 / Revised: 4 Dec. 2012 / Accepted: 18 Jan. 2013 / Published: 8 Apr. 2013

Index Terms

Bangla, Handwriting Style, Degenerated Lower Chain, Connected Digits


Segmentation of handwritten input into individual characters is a crucial step in connected handwriting recognition systems. In this paper we propose a robust scheme to segment handwritten Bangla numbers (numerical strings) against the variability involved in the writing style of different individuals. The segmentation of digits from a number is usually very tricky, as the digits in a Bangla number are seldom vertically separable. We have introduced the concept of Degenerated Lower Chain (DLC) for this purpose. The DLC method was proved efficient in case of segmenting handwriting digits in our experiments. Ten pages of handwritten Bangla numerical strings containing 2000 individual digits that construct 700 numbers written by five different writers of variable ages were segmented by the developed system. The system achieves more than 90% segmentation accuracy on average.

Cite This Paper

Md. Aktaruzzaman, Md. Farukuzzaman Khan, Ahsan-Ul-Ambia, "A New Technique for Segmentation of Handwritten Numerical Strings of Bangla Language", International Journal of Information Technology and Computer Science(IJITCS), vol.5, no.5, pp.38-43, 2013. DOI:10.5815/ijitcs.2013.05.05


[1]M. S Islam. Research on Bangla Language Processing in Bangladesh: Progress and Challenges 8th International Language and Development Conference, 23-25, June 2009, Dhaka, Babgladesh

[2]U. Pal and Sagarika Datta. Segmentation of Bangla Unconstrained Handwritten Text. Proceedings of the Seventh International Conference on Document Analysis and Recognition ICDAR 2003, IEEE, 0-7695-1960-1/03, 2003. 

[3]M Badruddoza, Reocgnition of Bangla handwritten letters using self-organizing map(SOM). Proceeding of 6th International Conference on Computer and Information Technology(ICCIT),PP. 357-360.

[4]A. O. M. Asaduzzaman, Mst Shayeala Parveen, and M Ganjer Ali. Detection of Bangla Numbers Using Artificial Neural Network. 6th ICCIT-2003, Jahangirnagar University, Dhaka, Bangladesh, pp347-350, 2003.

[5]Md. Farukuzzaman Khan, Md. Mizanur Rahman, Md. Aktaruzzaman, Md. Robiul Hoque, Md. Monirul Islam. System Development For Optical Character Recognition in Bangla, Journal Of Applied Science And Technology, Islamic University Studies, Vol-3, Part-1

[6]Md. Khademul Islam Molla and Kamrul Hasan Talukder. Bangla Number Extraction and Recognition from Document Image. 5th ICCIT 2002, East West University, 27-28 December 2002. 

[7]Thomas M. Brueuel. Segmentation of Handprinted Letter Strings using a Dynamic Programming Algorithm. Website: tbreuel@parc.xerox.com, Xerox PARC, Palo Alto, CA, USA.

[8]Md. Rafiul Hasan, Mohammad Azizul Haque and Syeda Umme Farhana Malik. Bangla Optical Character Recognition System. International Conference on Computer and Information Technology, ICCIT’99, SUST, Bangladesh, pages 164-168, December 1999.

[9]B B Chaudhury, U Pal and M Mitra. Automatic Recognition of Printed Oriya script”, Sadhana Vol. 27, Part 1, pp. 23-34. India, February 2002.

[10]Michael J. Laszlo. Computational Geometry and Computer Graphics In C++. Second Edition, Prentice-Hall of India Private Ltd., February-2002.

[11]Rafael C. Gonzalez. Digital Image Processing. 3rd Edition, PHI Learning Private Limited, New Delhi, 2008.