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

Recognition of Handwritten Gurmukhi Numeral using Gabor Filters

International Journal of Computer Applications
© 2012 by IJCA Journal
Volume 47 - Number 1
Year of Publication: 2012
Sukhpreet Singh
Renu Dhir

Sukhpreet Singh and Renu Dhir. Article: Recognition of Handwritten Gurmukhi Numeral using Gabor Filters. International Journal of Computer Applications 47(1):7-11, June 2012. Full text available. BibTeX

	author = {Sukhpreet Singh and Renu Dhir},
	title = {Article: Recognition of Handwritten Gurmukhi Numeral using Gabor Filters},
	journal = {International Journal of Computer Applications},
	year = {2012},
	volume = {47},
	number = {1},
	pages = {7-11},
	month = {June},
	note = {Full text available}


Isolated handwritten character recognition has been the subject of intensive research during the last decades because it is useful in wide range of real world problems. It also provides a solution for processing large volumes of data automatically. There is an emerging trend in the research of recognizing handwritten characters and numerals of many Indian languages and scripts. In this paper, two different feature sets based on Gabor filter have been used for recognition. One is being GABM having dimensionality 210 and other being GABN with dimensionality 200. The SVM classifier with RBF (Radial Basis Function) kernel is used for classification. The performance of the Gabor filter is tested on the database consisting of 1500 samples for basic 10 numerals of Gurmukhi script, collected from different writers. By using 7-fold cross validation, accuracy of 99. 53% using second feature set and 98. 4% using first feature set are observed. To obtain better results preprocessing of noise removal and normalization processes before feature extraction are recommended.


  • Plamondon, R. , and Srihari, S. N. , IEEE Trans on PAMI, vol. 22, pp. 62-84, 2000 On-Line and off-line handwritten recognition: A comprehensive survey.
  • Bhowmick, T. K. , et al. , Proc. 9th Int. Conf. on Information Technology, pp. 105-110, 2006. An HMM based recognition scheme for handwritten Oriya numerals.
  • Sharma, N. , Pal, U. , and Kimura, F. , Proc. 9th Int. Conf. On Information Technology, pp. 133-136, 2006. Recognition of handwritten Kannada numerals.
  • Bajaj, R. , Dey, L. and Chaudhury, S. , Sadhana, vol. 27, pp. -59-72, 2002. Devnagari numeral recognition by combining decision of multiple connectionist classifiers.
  • Bhattacharya, U. et al. , In Proc. 10th IWFHR, pp. 613-618, 2006. Neural combination of ANN and HMM for handwritten Devnagari Numeral Recognition.
  • Jangid, M. , Singh, K. , Dhir, R. , and Rani, R. , Internation Journal of Computer Applications (IJCA), Vol. 22, No. 1, May 2011. Performance Comparison of Devanagari Handwritten Numerals Recognition.
  • Sharma, D. , Lehal,G. S. , Preety Kathuria, MORC Spain, 2009. Digit Extraction and Recognition from Machine Printed Gurmukhi Documents.
  • Ubeeka Jain, Sharma, D. , International Journal of Computer Applications (IJCA), Vol. 4, No. 8, 2010. Recognition of Isolated Handwritten Characters of Gurumukhi Script using Neocognitron.
  • Siddharth, K. K. , Dhir, R. , and Rani, R. , International Journal of Computer Application (IJCA), Vol. 28, No. 2, August 2011. Handwritten Gurmukhi Numeral Recognition using Different Feature Sets.
  • Suen, C. Y. , Signal Process. 4, 193-207(1982). Distinctive features in the automatic recognition of handwritten characters.
  • Daugman, J. G. , J. Opt. Soc. Am. A, Vol. 2, No. 7, July 1981. 1. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters.
  • Hamamoto, Y. , Uchimura, S. , Pattern Recognition, Vol 19, pp. 45-52, 2001. A Gabor filter-based method for recognizing handwritten numbers.
  • Gabor, D. , J. IEE, Vo1. 93, pp. 429-459, 1946. Theory of communication.
  • Daugman, J. G. , IEEE Trans. onASSP, Vo1. 36, No. 7, pp. 1169-1179, 1988. Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression.
  • Chang, C. C. , and Lin, C. J. , 2001. LIBSVM: a library for support vector machines. Software available at http://www. csie. ntu. edu. tw/~cjlin/libsvm.
  • Hsu, C. W. , Chang, C. C. , and Lin, C. J. , A Practical Guide to Support Vector Classification", [Online]. Available at : http://www. csie. ntu. edu. tw/~cjlin/papers/ guide/guide. pdf.