Character Analysis using Matra Segmentation Algorithms for Distorted Tamil Characters

R. Indra Gandhi*, K. Iyakutti**
*Research Scholar, Department of Computer Science, Mother Teresa Women's University.
**CSIR Emeritus Scientist, School of Physics, Madurai Kamaraj University.
Periodicity:October - December'2009
DOI : https://doi.org/10.26634/jse.4.2.1074

Abstract

Segmentation is an important phase towards designing an optical character recognition system. Most of the segmentation algorithms primarily aim at segmenting text, graphics, page, line and word. It is a critical step as most recognition errors occur due to incorrect segmentation of characters. Character segmentation is the fundamental process in character recognition approaches, which rely on isolated characters. The accuracy of the text recognition system heavily depends on character segmentation.  All the techniques that already exist do not work well when the document contains distorted characters. Special care on “Matra” is needed to segment distorted characters. In this paper, we have empirically implemented algorithms for solving the key problems of distorted characters segmentation. Experimental results show that the proposed technique is accurate, easy for extension, and may be very effective for non-headline based complex Indic scripts.

Keywords

Segmentation, Character Segmentation, Distorted Character Segmentation, Matra, Non-Headline Scripts.

How to Cite this Article?

R. Indra Gandhi, K. Iyakutti (2009). Character Analysis using Matra Segmentation Algorithms for Distorted Tamil Characters, i-manager’s Journal on Software Engineering, 4(2),74-81. https://doi.org/10.26634/jse.4.2.1074

References

[2]. B. B. Chaudhuri and U. Pal, (1998), “A complete printed Bangla OCR system”, Pattern Recognition, Vol. 31(5), pp. 531-549.
[2]. B. B. Chaudhuri and U. Pal, (1998), “A complete printed Bangla OCR system”, Pattern Recognition, Vol. 31(5), pp. 531-549.
[3]. B. B. Chaudhuri, U. Pal and M. Mitra, (2001), “Automatic recognition of printed Oriya script”, in the th Proceedings of 6 ICDAR, pp. 795-799.
[4]. C. E. Dunn and P. S. P. Wang, (1992), “Character segmentation techniques for handwritten text - a survey”, in the Proceedings of ICPR, Vol. 2, pp. 577- 580.
[5]. Cheng, C.K., and Blumenstein, M.M., (2005), “Improving the Segmentation of Cursive Handwritten Words using Ligature Detection and Neural Validation”, th The 4 Asia Pacific International Symposium on Information Technology.
[6]. D. G. Elliman and I. T. Lancaster, (1990), “A review of segmentation and contextual analysis techniques for text recognition,” Pattern Recognition, Vol. 23, No. 3/4, pp. 337346.
[7]. E. Lecolinet and J. Crettez, (1991), “A graphemebased segmentation technique for cursive script recognition,” First Int'l Con$ Document Analysis and Recognition, Saint-Marlo, France, September, pp. 740-748.
[8]. Elnagar, A., and Alhajj, R., (2003), “Segmentation of connected handwritten numeral strings”. Pattern Recognition 36(3): 625-634.
[9]. G. S. Lehal, C. Singh and R. Lehal, (2001), “A Shape based post processor for Gurmukhi OCR”, in the th Proceedings of 6 ICDAR, pp. 1105-1109.
[10]. H. Fujisawa, Y. Nakano, and K. Kurino, (1992), “Segmentation methods for character recognition: From segmentation to document structure analysis,” Proc. IEEE, Vol. 80, pp. 10791092, July.
[11]. J. Dholakia, A. Negi and S. R. Mohan, (2005), “Zone identification in the printed Gujarati text”, in the th Proceedings of 8 ICDAR, pp. 272-276.
[12]. J. Rocha and T. Pavlidis, (1994), “A Shape analysis model with applications to a character recognition system”, IEEE Transactions on PAMI, Vol. 16(4), pp. 393- 404.
[13]. R. G. Casey and E. Lecolinet, (1996), “A Survey of methods and strategies in character segmentation”, IEEE Transactions on PAMI, Vol. 18(7), pp. 690-706.
[14]. R. L. Hoffman and J. W. McCullough, (1971), “Segmentation methods for recognition of machineprinted characters”, IBM Journal of Research and Development, Vol. 15(2), pp. 153-165.
[15]. R.G. Casey and G. Nagy, (1982), “Recursive segmentation and classification of composite character pattems,” Proc. Sixth International Conference on Pattern Recognition, pp. 1023-1026, Munich.
[16]. S. Kahan, T. Pavlidis and H. S. Baird, (1987), “On the recognition of printed characters of any font and size”, IEEE Trans. Pattern Anal. Mach. Intell. 9, March, pp. 274-288.
[17]. S. O. Belkasim, M. Shridhar and M. Ahmadi, (1991), “Pattern recognition with moment invariants: a comparative study and new results”, Pattern Recognition, Vol. 24(12), pp. 1117-1138.
[18]. S. Tsujimoto and H. Asada, (1991), “Resolving ambiguity in segmenting touching characters,” First Int'l Con$ Document Analysis and Recognition, Saint- Marlo, France, September, pp. 701-709.
[19]. T. Hong, (1995), “Degraded Text Recognition using Visual and Linguistic Context”, Ph. D. thesis, Computer Science Department of SUNY at Buffalo.
[20]. U. Pal and B. B. Chaudhuri, (1999), “Automatic separation of machine-printed and handwritten text th lines”, in the Proceedings of 5 ICDAR, pp. 645-648.
[21]. U. Pal and S. Datta, (2003), “Segmentation of Bangla unconstrained handwritten text”, in the th Proceedings of 7 ICDAR, pp. 1128-1132.
[22]. U. Pal, S. Sinha and B. B. Chaudhuri, (2003), “Multiscript line identification from Indian documents”, in the th Proceedings of 7 ICDAR, pp. 880-884.
[23]. V. Bansal, (1999), “Integrating Knowledge Sources in Devanagari Text Recognition”, Ph. D. thesis, IIT Kanpur, India.
[24]. Y. Lu and M. Shridhar, (1996), “Character segmentation in handwritten words an overview”, Pattern Recognition, Vol. 29(1), pp. 77-96.
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.