Character Segmentation on Degraded Printed ODIA Script
DOI:
https://doi.org/10.26438/ijcse/v8i4.4345Keywords:
Character segmentation, Connected Components, Degraded Script, Optical Character Segmentation, Odia ScriptAbstract
In this paper segmentation procedure of degraded script have been proposed of Odia script. A dataset of 50 documents including 170 words in each document making of 5000 character have been taken after scanning. After that segmentation procedure have been applied to get the accuracy rate of degraded printed Odia script. Also, different level of degradation in a script have been mentioned. Character segmentation on degraded odia printed script have been a tough task due to its Curvy with round format. Due to this style of writing it becomes difficult to segment its Characters. Character Segmentation is an essential part of Optical Character Recognition. Optical Character Recognition is an emerging area of research which helps in converting scanned image or handwritten notes into digital format.
References
[1] O. D. Trier, A. K. Jain and T. Taxt, “Feature extraction methods for character recognition: – A survey”, Pattern Recognition, Vol. 29(4), pp. 641-662, 1996.
[2] C. Y. Suen, “Character Recognition by Computer and Applications”, in Handbook of Pattern Recognition and Image Processing, New York: Academic pp. 569-586, 1986.
[3] S. Impedovo, L. Ottaviano and S. Occhinegro, “Optical Character Recognition - A Survey”, International Journal of Pattern Recognition & Artificial Intelligence, Vol. 5, pp. 1-24, 1991.
[4] P.Dussawar at. Al.Text Extraction from Complex Color Image Using Optical Character Recognition”, Vol.4, pp.730-735, 2015.
[5] U. Pal1, at al., A System for Off-line Oriya Handwritten Character Recognition using Curvature Feature ,IEEE,2007.
[6] Isha Sehgal and K.S. Venkatesh ,”Connected Component Labeling For Binary Images.”, International Journal Of Advanced Research, Int.J. of Adv. Res. 7 (8). 916-927.
[7] A. Amin, “Recognition of printed Arabic text based on global features and decision tree learning techniques”, Pattern Recognition, Vol. 33, pp. 1309-1323, 2000.
[8] S. Kahan, T. Pavlidis and H. S. Baird, “On the Recognition of Printed Characters of Any Font and Size”, IEEE Transactions on PAMI, Vol. 9(2), pp. 274- 288, 1987.
[9] M. K. Jindal, G. S. Lehal and R. K. Sharma, “Segmentation Problems and Solutions in Printed Degraded Gurmukhi Script”, International Journal of Signal Processing, Vol. 2(4), pp. 258-267, 2005.
[10] P. D. Gadar, M. Mohamed, and J. H. Chiang, “Handwritten Word Recognition with Character and Inter-Character Neural Networks”, IEEE Transactions on Systems, Man, and Cybernetics-Part B:Cybernetics, Vol. 27(1), pp. 158-164, 1997.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
