Advertisement

ShonkhaNet: A Dynamic Routing for Bangla Handwritten Digit Recognition Using Capsule Network

  • Sadeka HaqueEmail author
  • AKM Shahariar Azad RabbyEmail author
  • Md. Sanzidul Islam
  • Syed Akhter Hossain
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1037)

Abstract

In the present world, one of the most interesting topics is Handwritten Recognition due to its academic and commercial interest in different research fields. But deal with it a little bit tough because of different size and style. There are many works have been accomplished base in handwritten recognition including Bangla. Here proposed a model which is classified Bangla handwritten numeral using capsule net (a new type of neural network represents activity vector as parameters). The Model is trained and valid with ISI handwritten database [1], BanglaLekha Isolated [2], CMATERdb 3.1.1 [3] and all database together that was achieved 99.28% validation accuracy on ISI handwritten character database, 97.62% validation accuracy on BanglaLekha Isolated, 98.33% validation accuracy on CMATERdb 3.1.1 dataset and 98.90% validation accuracy combination mixed dataset. This model gives satisfactory recognition accuracy compared to other existing models.

Keywords

Bangla numeral Bangla handwritten recognition Pattern recognition Capsule CapsNet 

References

  1. 1.
    Bhattacharya, U., Chaudhuri, B.: Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Mach. Intell. 31, 444–457 (2009).  https://doi.org/10.1109/TPAMI.2008.88CrossRefGoogle Scholar
  2. 2.
    Biswas, M., et al.: BanglaLekhaIsolated: a multi-purpose comprehensive dataset of Handwritten Bangla Isolated characters. Data in Brief 12, 103–107 (2017).  https://doi.org/10.1016/j.dib.2017.03.035CrossRefGoogle Scholar
  3. 3.
    Sarkar, R., Das, N., Basu, S., Kundu, M., Nasipuri, M., Basu, D.K.: CMATERdb1: a database of unconstrained handwritten Bangla and Bangla-English mixed script document image. Int. J. Doc. Anal. Recogn. (IJDAR) 15(1), 71–83 (2012)CrossRefGoogle Scholar
  4. 4.
    Cheriet, M., Yacoubi, M.E., Fujisawa, H., Lopresti, D., Lorette, G.: Handwritten recognition research: Twenty years of achievement... and beyond. Pattern Recogn. 42, 3131–3135 (2009)CrossRefGoogle Scholar
  5. 5.
    Dong, J., Krzyżak, A., Suen, C.Y.: An improved handwritten Chinese character recognition system using support vector machine. Pattern Recogn. Lett. 26(12), 1849–1856 (2005)CrossRefGoogle Scholar
  6. 6.
    Zhu, B., Zhou, X.-D., Liu, C.-L., Nakagawa, M.: A robust model for on-line handwritten Japanese text recognition. IJDAR 13(2), 121–131 (2010)CrossRefGoogle Scholar
  7. 7.
    Kim, H.J., Kim, P.K.: Recognition of off-line handwritten Korean characters. Pattern Recogn. 29, 245–254 (1996)CrossRefGoogle Scholar
  8. 8.
    Geoffrey, E.H., et al.: Dynamic Routing Between Capsules. 1710.09829v2 [cs.CV], 7 November 2017Google Scholar
  9. 9.
    Hinton, G.E., Krizhevsky, A., Wang, S.D.: Transforming auto-encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 44–51. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-21735-7_6CrossRefGoogle Scholar
  10. 10.
    Pal, U., Chaudhuri, B.B.: Automatic recognition of unconstrained off-line Bangla handwritten numerals. In: Tan, T., Shi, Y., Gao, W. (eds.) ICMI 2000. LNCS, vol. 1948, pp. 371–378. Springer, Heidelberg (2000).  https://doi.org/10.1007/3-540-40063-X_49CrossRefGoogle Scholar
  11. 11.
    Alom, M.Z., Sidike, P., Taha, T.M., Asari, V.: Handwritten Bangla Digit Recognition Using Deep Learning (2017)Google Scholar
  12. 12.
    Rabby, A.K.M.S.A., Abujar, S., Haque, S., Hossain, S.A.: Bangla handwritten digit recognition using convolutional neural network. In: Abraham, A., Dutta, P., Mandal, J.K., Bhattacharya, A., Dutta, S. (eds.) Emerging Technologies in Data Mining and Information Security. AISC, vol. 755, pp. 111–122. Springer, Singapore (2019).  https://doi.org/10.1007/978-981-13-1951-8_11CrossRefGoogle Scholar
  13. 13.
    Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs.LG], December 2014
  14. 14.
    Janocha, K., Czarnecki, M.W.: On loss functions for deep neural networks in classification. arxiv, abs/1702.05659 (2017)Google Scholar
  15. 15.
    Khan, H.A., Al Helal, A., Ahmed, K.I.: Handwritten Bangla digit recognition using sparse representation classifier. In: 2014 International Conference on Informatics, Electronics & Vision (ICIEV), pp. 1–6. IEEE (2014)Google Scholar
  16. 16.
    Wen, Y., He, L.: A classifier for Bangla handwritten numeral recognition. Expert Syst. Appl. 39(1), 948–953 (2012)CrossRefGoogle Scholar
  17. 17.
    Nasir, M.K., Uddin, M.S.: Handwritten Bangla numerals recognition for automated postal system. IOSR J. Comput. Eng. 8(6), 43–48 (2013)CrossRefGoogle Scholar
  18. 18.
    Islam, S., Shill, P.C., Rahman, M.M., Akhand, M.A.H., Rahman, M.M.H.: Bangla handwritten character recognition using convolutional neural network. Int. J. Image Graphics Signal Process. (IJIGSP) 73, 42–49 (2015)Google Scholar
  19. 19.
    Sarkhel, R., Das, N., Saha, A.K., Nasipuri, M.: A multi-objective approach towards cost-effective isolated handwritten Bangla character and digit recognition. Pattern Recogn. 58, 172–189 (2016)CrossRefGoogle Scholar
  20. 20.
    Basu, S., Sarkar, R., Das, N., Kundu, M., Nasipuri, M., Basu, D.K.: Handwritten Bangla digit recognition using classifier combination through DS Technique. In: Pal, S.K., Bandyopadhyay, S., Biswas, S. (eds.) PReMI 2005. LNCS, vol. 3776, pp. 236–241. Springer, Heidelberg (2005).  https://doi.org/10.1007/11590316_32CrossRefGoogle Scholar
  21. 21.
    Santosh, K.C., Wendling, L.: Character recognition based on non-linear multi-projection profiles measure. Front. Comput. Sci. 9, 678–690 (2015)CrossRefGoogle Scholar
  22. 22.
    Deans, S.R.: Applications of the Radon Transform. Wiley Interscience Publications, New York (1983)zbMATHGoogle Scholar
  23. 23.
    Santosh, K.C.: Character recognition based on DTW-radon. In: 2011 International Conference on Document Analysis and Recognition. IEEE (2011)Google Scholar
  24. 24.
    Kruskall, J.B., Liberman, M.: The symmetric time warping algorithm: From continuous to discrete. In: Time Warps, String Edits and Macromolecules: The Theory and Practice of String Comparison, pp. 125–161. Addison-Wesley, Boston (1983)Google Scholar
  25. 25.
    Hassan, T., Khan, H.A.: Handwritten bangla numeral recognition using local binary pattern. In: 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), pp. 1–4. IEEE (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringDaffodil International UniversityDhakaBangladesh

Personalised recommendations