Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

Recognition of Individual Handwritten Letters of the Farsi Language using a Decision Tree

Print
PDF
 
Download Full Text
International Journal of Computer Applications
© 2012 by IJCA Journal
Volume 55 - Number 5
Year of Publication: 2012
Authors:
Atefe Matin Niya
Hedieh Sajed
10.5120/8749-2636

Atefe Matin Niya and Hedieh Sajed. Article: Recognition of Individual Handwritten Letters of the Farsi Language using a Decision Tree. International Journal of Computer Applications 55(5):7-11, October 2012. Full text available. BibTeX

@article{key:article,
	author = {Atefe Matin Niya and Hedieh Sajed},
	title = {Article: Recognition of Individual Handwritten Letters of the Farsi Language using a Decision Tree},
	journal = {International Journal of Computer Applications},
	year = {2012},
	volume = {55},
	number = {5},
	pages = {7-11},
	month = {October},
	note = {Full text available}
}

Abstract

In this study, in order to recognize Farsi handwritten letters, firstthe pre-processing operation is done on the letters' images including normalization, thinning, reduction, noise reduction, etc. ,and then the feature vector of the letters is extracted using the first to the forth momentums fromthe second level of wavelet transform and contourlettransform. A combination of decision-tree methods is used for the final recognition of letters. The database used in this study is the "Hoda" handwritten letter collection. The mean recognition rate in this combinational method is 97. 89%.

References

  • F. Solimanpour, J. Sadri, C. Y. Suen, "Standard databases forrecognition of handwritten digits, numerical strings, legalamounts, letters and dates in Farsi language", in: Proceedings of the10th International Workshop on Frontiers of Handwriting Recognition, La Baule, France, 2006, pp. 3–7
  • M. Hanmandlu, O. V. Ramana Murthy, Vamsi KrishnaMadasu,"Fuzzy Model based recognition of handwrittenHindi characters", Digital Image Computing Techniquesand Applications, 0-7695-3067-2/07 © 2009 IEEE.
  • Abulhaiba S. H. , Mahmood S. A. , Green R. J. , "Recognition of handwritten cursiveArabic characters", IEEE Trans. On PAMI, Vol. 16, No. 6, pp. 664-671, 1994.
  • Altuwaijir M. and Bayoumi M. , "Arabic text recognition using neural networks",Proc. Int. Symp. On Circuit and Systems (ISCAS'94), pp. 415-418, 1994.
  • R. Plamondon; S. Srihari; "On-line andOff-line Handwritten Recognition: AComprehensive Survey"; IEEE Trans. On Pattern Analaysis and MachineIntelligence; Vol. 22; No. 1; January 2000;pp. 63-83.
  • N. Arica; F. T. Yarman-Vural; "Anoverview of caracter recognition focusedon off-line handwriting"; IEEE Trans. OnSystems; Man and Cybernetics-Part C:Application and Reviews; Vol. 31; No. 2;May 2009; pp. 216-233.
  • M. Ziaratban, K. Faez, F. Faradji, "Language-based featureextraction using template-matching in Farsi/Arabic handwrittennumeral recognition", in: Proceedings of the 9th InternationalConference on Document Analysis and Recognition, vol. 1,Curitiba, Brazil, 2007, pp. 297–301.
  • Teltscher, H. O. "Handwriting-Revelation ofSelf", Hawthorn Books Inc. Publishers, New York,1971.
  • J. C. Simon. , "Off-line cursive word recognition. Proc". IEEE, 80(7):1150–1160,1992.
  • Tal Steinherz, Nathan Intrator, and Ehud Rivlin. "Skew detection via principalcomponents analysis. In Proceedings of the 5th International Conferenceon Document Analysis and Recognition", pages 153–156. IEEE Computer Society
  • Ebrahimi. A. Kabir. E. ,"A pictorial dictionary for printed Farsi sub words", Pattern Recognition Letters 29 (2008) 656–663.
  • R. Jacobs, "Methods for combining expert's probability assessments", Neural Computation, vol. 7, pp. 867-888, 1995.