Unconstrained Kannada Handwritten Character Recognition Using Multi-level SVM Classifier

  • G. G. Rajput
  • Rajeshwari Horakeri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


This paper presents an efficient zoning based method for recognition of handwritten Kannada characters using two sets of features, namely, crack codes (the line between the object pixel and background) and the density of the object pixels. A multi-level SVM is used for the classification purpose. The proposed method is implemented in two stages. In the first stage, similar shaped characters are combined into groups resulting in 22 classes instead of 49 classes, one class per character. Crack codes are used to assign the input character image to one of the groups. In the second stage, object pixel density is used to assign label to the input character image within that identified group. Experiments are performed on handwritten Kannada characters consisting of 24500 images with 500 samples for each character. Five-fold cross validation is used for result computation and average recognition rate of 91.02 % is obtained.


Kannada Crack codes SVM handwritten character five-fold cross validation 


  1. 1.
    Nagy, G.: Chinese character recognition, A twenty five years retrospective. In: Proceedings of ICPR, pp. 109–114 (1988)Google Scholar
  2. 2.
    Lorigo, L.M., Govindaraju, V.: Offline Arabic handwriting recognition: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(5), 712–724 (2006)CrossRefGoogle Scholar
  3. 3.
    Pal, A., Singh, D.: Handwritten English Character Recognition Using Neural Network. International Journal of Computer Science & Communication 1, 141–144 (2010)Google Scholar
  4. 4.
    Indira, K., Sethu Selvi, S.: Kannada Character Recognition System: A Review. Inter JRI Science and Technology 1(2), 31–42 (2009)Google Scholar
  5. 5.
    Pal, U., Chaudhuri.: Indian script character recognition: a survey. Pattern Recognition 37(9), 1887–1899 (2004)Google Scholar
  6. 6.
    Holambe, A.N., Thool, R.C., Jagade, S.M.: Printed and Handwritten Character & Number Recognition of Devanagari Script using Gradient Features. International Journal of Computer Applications 2(9), 975–8887 (2010)CrossRefGoogle Scholar
  7. 7.
    Pal, U., Wakabayashi, T., Kimura, F.: Handwritten Bangla Compound Character Recognition Using Gradient Feature. In: 10th International Conference on Information Technology (ICIT 2007), December 17-20, pp. 208–213 (2007)Google Scholar
  8. 8.
    Bhattacharya, U., Shridhar, M., Parui, S.K.: On Recognition of Handwritten Bangla Characters. In: Kalra, P.K., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338, pp. 817–828. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Hanmandlu, M., Ramana Murthy, O.V., Madasu, V.K.: Fuzzy Model based recognition of handwritten Hindi characters. In: 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications, December 3-5, pp. 454–461. IEEE (2007)Google Scholar
  10. 10.
    Pal, U., Sharma, N., Wakabayashi, T., Kimura, F.: Handwritten Character Recognition of Popular South Indian Scripts. In: Doermann, D., Jaeger, S. (eds.) SACH 2006. LNCS, vol. 4768, pp. 251–264. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Niranjan, S.K., Kumar, V., Hemantha Kumar, G., Aradhya, M.: FLD based Unconstrained Handwritten Kannada Character Recognition. International Journal of Database Theory and Application 2(3) (September 2009)Google Scholar
  12. 12.
    Dhandra, B.V., Hangarge, M., Mukarambi, G.: Spatial Features for Handwritten Kannada and English Character Recognition. IJCA, Special Issue on RTIPPR (3), 146–151 (2010)Google Scholar
  13. 13.
    Ragha, L.R., Sasikumar, M.: Feature Analysis for Handwritten Kannada Kagunita Recognition. International Journal of Computer Theory and Engineering, IACSIT 3(1), 1793–8201 (2011)Google Scholar
  14. 14.
    Aradhya, M., Niranjan, S.K., Hemant Kumar, G.: Probablistic Neural Network based Approach for Handwritten Character Recognition. Special Issue of IJCCT 1(2,3,4); 2010 for International Conference (ACCTA 2010), August 3-5, pp. 9–13 (2010)Google Scholar
  15. 15.
    Kumar, S., Kumar, A., Kalyan, S.: Kannada Character Recognition System using Neural Network. National Journal on Internet Computing 1, 33–35Google Scholar
  16. 16.
    Gonzalez, R.C.G., Woods, R.E.: Digital Image Processing, 2nd edn. Pearson Education Asia (2002)Google Scholar
  17. 17.
    Alaei, A., Nagabhushan, P., Pal, U.: Fine classification of Handwritten Persian/Arabic Numerals by Removing Confusion amongst Similar Classes. In: 10th International Conference on Document Analysis and Recognition, ICDAR, pp. 601–605Google Scholar
  18. 18.
    Rajput, G.G., Horakeri, R.: Handwritten Kannada Vowel Character Recognition System using Crack code and Fourier Descriptors. In: Sombattheera, C., Agarwal, A., Udgata, S.K., Lavangnananda, K. (eds.) MIWAI 2011. LNCS, vol. 7080, pp. 169–180. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  19. 19.
    Vapnik, V.N.: The Statistical Learning Theory. Springer, Berlin (1998)Google Scholar
  20. 20.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 144–152 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • G. G. Rajput
    • 1
  • Rajeshwari Horakeri
    • 1
  1. 1.Department of Computer ScienceGulbarga UniversityGulbargaIndia

Personalised recommendations