Weka-Based Classification Techniques for Offline Handwritten Gurmukhi Character Recognition

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 236)

Abstract

In this paper, we deal with weka-based classification methods for offline handwritten Gurmukhi character recognition. This paper presents an experimental assessment of the effectiveness of various weka-based classifiers. Here, we have used two efficient feature extraction techniques, namely, parabola curve fitting based features, and power curve fitting based features. For recognition, we have used 18 different classifiers for our experiment. In this work, we have collected 3,500 samples of isolated offline handwritten Gurmukhi characters from 100 different writers. We have taken 60 % data as training data and 40 % data as testing data. This paper presents a novel framework for offline handwritten Gurmukhi character recognition using weka classification methods and provides innovative benchmark for future research. We have achieved a maximum recognition accuracy of about 82.92 % with parabola curve fitting based features and the multilayer perceptron model classifier. In this work, we have used C programming language and weka classification software tool. At this point, we have also reported comparative study weka classification methods for offline handwritten Gurmukhi character recognition.

Keywords

Handwritten character recognition Feature extraction Classification Weka Tool 

References

  1. 1.
    Aradhya, V.N.M., Kumar, G.H., Noushath, S.: Multilingual OCR system for south Indian scripts and English documents: an approach based on Fourier transform and principal component analysis. Eng. Appl. Artif. Intell. 21, 658–668 (2008)CrossRefGoogle Scholar
  2. 2.
    Bansal, V., Sinha, R.M.K.: Integrating knowledge sources in devanagari text recognition. IEEE Trans. Syst. Man Cybern. 30(4), 500–505 (2000)Google Scholar
  3. 3.
    Bansal, V., Sinha, R.M.K.: Segmentation of touching and fused Devanagri characters. Pattern Recogn. 35(4), 875–893 (2002)CrossRefMATHGoogle Scholar
  4. 4.
    Chaudhuri, B.B., Majumder, D.D., Parui, S.K.: A procedure for recognition of connected hand written numerals. Int. J. Syst. Sci. 13, 1019–1029 (1982)CrossRefGoogle Scholar
  5. 5.
    Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29, 131–163 (1997)CrossRefMATHGoogle Scholar
  6. 6.
    Gader, P.D., Mohamed, M., Chaing, J.H.: Handwritten word recognition with character and inter-character neural networks. IEEE Trans. Syst. Man Cybern. Part B Cybern. 27(1), 158–164 (1997)CrossRefGoogle Scholar
  7. 7.
    Genkin, A., Lewis, D., Madigan, D.: Large-scale Bayesian logistic regression for text categorization. TECHNOME TRICS. 49(3), 291–304 (2004)Google Scholar
  8. 8.
    Hanmandlu, M., Grover, J., Madasu, V. K. and Vasikarla, S.: Input fuzzy for the recognition of handwritten Hindi numeral. In: Proceedings of ITNG, pp. 208–213 (2007)Google Scholar
  9. 9.
    Jomy, J., Parmod, K.V., Kannan, B.: Handwritten character recognition of south Indian scripts: a review. In: Proceedings of Indian Language Computing, pp. 1–6 (2011)Google Scholar
  10. 10.
    Kala, R., Vazirani, H., Shukla, A. and Tiwari, R.: Offline handwriting recognition using genetic algorithm. Int. J. Comput. Sci. Issues 7(2,1), 16–25 (2010)Google Scholar
  11. 11.
    Kumar, D.: AI approach to hand written Devanagri script recognition. In: Proceedings of 10th International conference on EC3-Energy, Computer, Communication and Control Systems, 2, 229–237 (2008)Google Scholar
  12. 12.
    Kumar, M., Jindal, M. K. and Sharma, R. K.: Review on OCR for handwritten Indian scripts character recognition. In: Proceedings of DPPR, pp. 268–276 (2011)Google Scholar
  13. 13.
    Kumar, M., Jindal, M.K., Sharma, R.K.: Efficient feature extraction technique for offline handwritten Gurmukhi character recognition. Chaing Mai J. Sci. (2012)Google Scholar
  14. 14.
    Lehal, G.S., Singh, C.: A Gurmukhi script recognition system. In: Proceedings of 15th ICPR, pp. 557–560 (2000)Google Scholar
  15. 15.
    McCallum, A., Nigam, K.: A comparison of event models for Naive Baye’s text classification. Paper presented at the workshop on learning for text categorization (1998)Google Scholar
  16. 16.
    Pal, U., Wakabayashi, T., Kimura, F.: Handwritten numeral recognition of six popular scripts. In: Proceedings of ICDAR, vol. 2, pp. 749–753 (2007a)Google Scholar
  17. 17.
    Pal, U., Wakabayashi, T., Kimura, F.: A system for off-line Oriya handwritten character recognition using curvature feature. In: Proceedings of 10th ICIT, pp. 227–229 (2007b)Google Scholar
  18. 18.
    Pal, U., Wakabayashi, T., Kimura, F.: Comparative study of devanagari handwritten character recognition using different feature and classifiers. In: Proceedings of 10th ICDAR, pp. 1111–1115 (2009)Google Scholar
  19. 19.
    Patel, C.I., Patel, R., Patel, P.: Handwritten character recognition using neural network. Int. J. Sci. Eng. Res. 2(4), 1–5 (2011)Google Scholar
  20. 20.
    Rajashekararadhya, S.V., Ranjan, S. V.: Zone based feature extraction algorithm for handwritten numeral recognition of Kannada script. In: Proceedings of IACC, pp. 525–528 (2009)Google Scholar
  21. 21.
    Roy, K., Alaei, A., Pal, U.: Word-wise handwritten Persian and Roman script identification. In: Proceedings of ICFHR, pp. 628–633 (2010)Google Scholar
  22. 22.
    Sharma, N., Pal, U., Kimura, F., Pal, S.: Recognition of off-line handwritten devanagari characters using quadratic classifier. In: Proceedings of ICVGIP, pp. 805–816 (2006)Google Scholar

Copyright information

© Springer India 2014

Authors and Affiliations

  1. 1.Department of Computer SciencePanjab University Rural CentreMuktsarIndia
  2. 2.Department of Computer Science and ApplicationsPanjab University Regional CentreMuktsarIndia
  3. 3.School of Mathematics and Computer ApplicationsThapar UniversityPatialaIndia

Personalised recommendations