Skip to main content
Log in

SVM-based hierarchical architectures for handwritten Bangla character recognition

  • Original Paper
  • Published:
International Journal on Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

We propose support vector machine (SVM) based hierarchical classification schemes for recognition of handwritten Bangla characters. A comparative study is made among multilayer perceptron, radial basis function network and SVM classifier for this 45 class recognition problem. SVM classifier is found to outperform the other classifiers. A fusion scheme using the three classifiers is proposed which is marginally better than SVM classifier. It is observed that there are groups of characters having similar shapes. These groups are determined in two different ways on the basis of the confusion matrix obtained from SVM classifier. In the former, the groups are disjoint while they are overlapped in the latter. Another grouping scheme is proposed based on the confusion matrix obtained from neural gas algorithm. Groups are disjoint here. Three different two-stage hierarchical learning architectures (HLAs) are proposed using the three grouping schemes. An unknown character image is classified into a group in the first stage. The second stage recognizes the class within this group. Performances of the HLA schemes are found to be better than single stage classification schemes. The HLA scheme with overlapped groups outperforms the other two HLA schemes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Chaudhuri B.B., Pal U.: A complete printed Bangla OCR system. Pattern Recognit. 31(5), 531–549 (1998)

    Article  Google Scholar 

  2. Plamondon R., Srihari S.N.: On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans. PAMI 22(1), 63–84 (2000)

    Google Scholar 

  3. Arica N., Vural F.Y.: An overview of character recognition focused on off-line handwriting. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 31(2), 216–233 (2001)

    Article  Google Scholar 

  4. Setlur S., Lawson A., Govindaraju V., Srihari S.: Large scale address recognition systems truthing, testing, tools, and other evaluation issues. Int. J. Doc. Anal. Recognit. (IJDAR) 4(3), 154–169 (2001)

    Article  Google Scholar 

  5. Gorski N., Anisimov V., Augustin E., Baret O., Maximov S.: Industrial bank check processing: the A2iA CheckReaderTM. IJDAR 3(4), 196–206 (2001)

    Article  Google Scholar 

  6. Oh I.S., Suen C.Y.: Distance features for neural network-based recognition of handwritten characters. IJDAR 1(2), 73–88 (1998)

    Article  Google Scholar 

  7. Nopsuwanchai, R., Povey, D.: Discriminative trainig for HMM-based offline handwritten character recognition. In: Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR), Scotland, pp. 114–118 (2003)

  8. Dong J.X., Zak A.K., Suen C.Y.: An improved handwritten Chinese character recognition system using support vector machine. Pattern Recognit. Lett. 26(12), 1849–1856 (2005)

    Article  Google Scholar 

  9. Camastra F.: A SVM-based cursive character recognizer. Pattern Recognit. 40, 3721–3727 (2007)

    Article  MATH  Google Scholar 

  10. Liu C.L., Nakashima K., Sako H., Fujisawa H.: Handwritten digit recognition: Benchmarking of state-of-the-art techniques. Pattern Recognit. 36(10), 2271–2285 (2003)

    Article  MATH  Google Scholar 

  11. Günter, S., Bunke, H.: Combination of three classifiers with different architectures for handwritten word recognition. In: Proceedings of the 9th IWFHR, pp. 63–68 (2004)

  12. Bellili A., Gilloux M., Gallinari P.: An MLP-SVM combination architecture for offline handwritten digit recognition: reduction of recognition errors by Support Vector Machines rejection mechanisms. IJDAR 5, 244–252 (2003)

    Article  Google Scholar 

  13. Milgram, J., Sabourin, R., Cheriet, M.: Two-stage classification system combining model-based and discriminative approaches. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR), pp. 152–155 (2004)

  14. Chellapilla, K., Shilman, M., Simard, P.: Combining multiple classifiers for faster optical character recognition. In: Proceedings of the 7th International Workshop Document Analysis Systems (DAS), New Zealand, pp. 358–367 (2006)

  15. Rahman F.R., Fairhurst M.C.: Multiple classifier decision combination strategies for character recognition: A review. IJDAR 5(4), 166–194 (2003)

    Article  Google Scholar 

  16. Rahman F.R., Rahman R., Fairhurst M.C.: Recognition of Handwritten Bengali characters: A novel multistage approach. Pattern Recognit. 35(3), 997–1006 (2002)

    Article  MATH  Google Scholar 

  17. Bhowmik, T.K., Bhattacharya, U., Parui, S.K.: Recognition of Bangla handwritten characters using an MLP classifier based on stroke features. In: Proceedings of the 11th International Conference on Neural Information Processing (ICONIP), India, pp. 814–819 (2004)

  18. Bhattacharya, U., Shridhar, M., Parui, S.K.: On recognition of handwritten Bangla characters. In: In: Kalra, P., Peleg, S. (eds.) Proceedings of the 5th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), Springer Lecture Notes on Computer Science, vol 4338, pp. 817–828 (2006)

  19. Hsu C.W., Lin C.J.: A comparison of methods for multiclass Support Vector Machines. IEEE Trans. Neural Netw. 13(2), 415–425 (2002)

    Article  Google Scholar 

  20. Bhattacharya, U., Chaudhuri, B.B.: Fusion of combination rules of an MLP classifiers for improved recognition accuracy of handprinted Bangla numerals. In: Proceedings of the 8th ICDAR, Korea I, pp. 322–326 (2005)

  21. Bhattacharya, U., Parui, S.K., Shaw, B., Bhattacharya K.: Neural combination of ANN and HMM for handwritten Devnagari numeral recognition. In: Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition (IWFHR), France, pp. 613–618 (2006)

  22. Daubechies I.: Ten lectures in Wavelets. CBMS-NSF Regional Conf. Series in Appl. Math. 4, 909–996 (1998)

    MathSciNet  Google Scholar 

  23. Haykin S.: Neural Networks: A Comprehensive Foundation. Prentice-Hall, Englewood Cliffs (1999)

    MATH  Google Scholar 

  24. Bhattacharya, U., Parui, S.K.: Self-adaptive learning rates in backpropagation algorithm improve its function approximation performance. In: Proceedings of the IEEE International Conference on Neural Networks, Australia, pp. 2784–2788 (1995)

  25. Vapnik V.: Statistical Learning Theory. Wiley, NY (1998)

    MATH  Google Scholar 

  26. Cristianini N., Shawe-Taylor J.: An introduction to support vector machine and other kernel based learning methods. Cambridge University Press, Cambridge (2000)

    Google Scholar 

  27. Joachims, T.: SVMlight: Support Vector Machine (2002)

  28. KreBel, U. (1999) Pairwise classification and support vector machines. In: Advances in Kernel Methods: Support Vector Learning, MIT Press, Cambridge, pp. 255–268

  29. Jain A.K., Dubes R.C.: Algorithms for Clustering Data. Prentice-Hall, NJ (1988)

    MATH  Google Scholar 

  30. Martinetz T.M., Berkovich S.G., Schulten K.J.: ‘Neural-gas” network for vector quantization and its application to time-series prediction. IEEE Trans. Neural Netw. 4(4), 558–569 (1993)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Swapan Kumar Parui.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bhowmik, T.K., Ghanty, P., Roy, A. et al. SVM-based hierarchical architectures for handwritten Bangla character recognition. IJDAR 12, 97–108 (2009). https://doi.org/10.1007/s10032-009-0084-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-009-0084-x

Keywords

Navigation