Advertisement

A Comparative Study of Different Feature Extraction Techniques for Offline Malayalam Character Recognition

  • Anitha Mary M. O. Chacko
  • P. M. Dhanya
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 32)

Abstract

Offline Handwritten Character Recognition of Malayalam scripts have gained remarkable attention in the past few years. The complicated writing style of Malayalam characters with loops and curves make the recognition process highly challenging. This paper presents a comparative study of Malayalam character recognition using 4 different feature sets—Zonal features, Projection histograms, Chain code histograms and Histogram of Oriented Gradients. The performance of these features for isolated Malayalam vowels and 5 consonants are evaluated in this study using feedforward neural networks as classifier. The final recognition results were computed using a 5 fold cross validation scheme. The best recognition accuracy of 94.23 % was obtained in this study using Histogram of Oriented Gradients features.

Keywords

Offline character recognition Feature extraction Neural networks 

References

  1. 1.
    Plamondan, R., Srihari, S.N.: Online and offline character recognition: a comprehensive survey. IEEE Trans. PAMI 22, 63–84 (2000)CrossRefGoogle Scholar
  2. 2.
    Lajish, V.L.: Handwritten character recognition using perpetual fuzzy zoning and class modular neural networks. In: Proceedings of 4th International National Conference on Innovations in IT, pp. 188–192 (2007)Google Scholar
  3. 3.
    John, R., Raju, G., Guru, D.S.: 1D wavelet transform of projection profiles for isolated handwritten character recognition. In: Proceedings of ICCIMA07, pp. 481–485, Sivakasi (2007)Google Scholar
  4. 4.
    Raju, G.: Wavelet transform and projection profiles in handwritten character recognition—a performance analysis. In: Proceedings of 16th International Conference on Advanced Computing and Communications, pp. 309–314, Chennai (2008)Google Scholar
  5. 5.
    John, J., Pramod K.V., Balakrishnan K.: Offline handwritten Malayalam character recognition based on chain code histogram. In: Proceedings of ICETECT (2011)Google Scholar
  6. 6.
    John, J., Pramod, K.V., Balakrishnan, K.: Unconstrained handwritten Malayalam character recognition using wavelet transform and support vector machine classifier. In: International Conference on Communication Technology and System Design, Elsevier (2011)Google Scholar
  7. 7.
    Moni, B.S., Raju, G.: Modified quadratic classifier and directional features for handwritten Malayalam character recognition. In: IJCA Special Issue on Computational Science—New Dimensions Perspectives NCCSE (2011)Google Scholar
  8. 8.
    John, J., Balakrishnan, K., Pramod, K.V.: A system for offline recognition of handwritten characters in Malayalam script. Int. J. Image Graph. Signal Process. 4, 53–59 (2013)CrossRefGoogle Scholar
  9. 9.
    Chacko, A.M.M.O.: Dhanya PM, Handwritten character recognition in Malayalam scripts—a review. Int. J. Artif. Intell. Appl. (IJAIA) 5(1), 79–89 (2014)Google Scholar
  10. 10.
    Trier, O.D., Jain, A.K., Taxt, J.: Feature extraction methods for character recognition—a survey. Pattern Recogn. 29(4), 641–662 (1996)CrossRefGoogle Scholar
  11. 11.
    Freeman, H.: On the encoding of arbitrary geometric configurations. IRE Trans. Electr. Comp. TC 10(2), 260–268 (1961)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 886–893 (2005)Google Scholar
  13. 13.
    Ludwig, O., Delgado, D., Goncalves, V., Nunes, U.: Trainable classifier-fusion schemes: an application to pedestrian detection. In: 12th International IEEE Conference on Intelligent Transport Systems, pp. 1–6 (2009)Google Scholar
  14. 14.
    Chacko, A.M.M.O., Dhanya, P.M.: A differential chain code histogram based approach for offline Malayalam character recognition. In: International Conference on Communication and Computing (ICC-2014), pp. 134–139 (2014)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringRajagiri School of Engineering and TechnologyKochiIndia

Personalised recommendations