Advertisement

A Study on the Effect of CNN-Based Transfer Learning on Handwritten Indic and Mixed Numeral Recognition

  • Rahul PramanikEmail author
  • Prabhat Dansena
  • Soumen Bag
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1020)

Abstract

Filling up forms at post offices, railway counters, and for application of jobs has become a routine for modern people, especially in a developing country like India. Research on automation for the recognition of such handwritten forms has become mandatory. This applies more for a multilingual country like India. In the present work, we use readily available pre-trained Convolutional Neural Network (CNN) architectures on four different Indic scripts, viz. Bangla, Devanagari, Oriya, and Telugu to achieve a satisfactory recognition rate for handwritten Indic numerals. Furthermore, we have mixed Bangla and Oriya numerals and applied transfer learning for recognition. The main objective of this study is to realize how good a CNN model trained on an entire different dataset (of natural images) works for small and unrelated datasets. As a part of practical application, we have applied the proposed approach to recognize Bangla handwritten pin codes after their extraction from postal letters.

Keywords

Alexnet CNN Handwritten numerals Transfer learning VGG-16 

References

  1. 1.
    Mahalat, M.H., Mollah, A.F., Basu, S., Nasipuri, M.: Design of novel post-processing algorithms for handwritten Arabic numerals classification. Int. J. Appl. Pattern Recognit. 4(4), 342–357 (2017)CrossRefGoogle Scholar
  2. 2.
    Prasad, B.K., Sanyal, G.: Novel features and a cascaded classifier based Arabic numerals recognition system. Multidimension. Syst. Signal Process. 29(1), 321–338 (2018)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Zhang, X.Y., Bengio, Y., Liu, C.L.: Online and offline handwritten Chinese character recognition: a comprehensive study and new benchmark. Pattern Recognit. 61, 348–360 (2017)CrossRefGoogle Scholar
  4. 4.
    Niu, X.X., Suen, C.Y.: A novel hybrid CNN-SVM classifier for recognizing handwritten digits. Pattern Recognit. 45(4), 1318–1325 (2012)CrossRefGoogle Scholar
  5. 5.
    Ouchtati, S., Redjimi, M., Bedda, M.: Realization of an offline system for the recognition of the handwritten numeric chains. In: Proceedings of the Iberian Conference on Information Systems and Technologies, pp. 1–6 (2014)Google Scholar
  6. 6.
    Chakraborty, D., Pramanik, R., Bag, S.: A novel approach towards segmentation of connected handwritten numerals. In: Proceedings of the International Conference on Image Information Processing, pp. 1–5 (2017)Google Scholar
  7. 7.
    Singh, P.K., Sarkar, R., Nasipuri, M.: Offline script identification from multilingual Indic-script documents: a state-of-the-art. Comput. Sci. Rev. 15, 1–28 (2015)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Pramanik, R., Bag, S.: Shape decomposition-based handwritten compound character recognition for Bangla OCR. J. Vis. Commun. Image Represent. 50, 123–134 (2018)CrossRefGoogle Scholar
  9. 9.
    Khan, H.A., Al Helal, A., Ahmed, K.I.: Handwritten Bangla digit recognition using sparse representation classifier. In: Proceedings of the International Conference on Informatics, Electronics and Vision, pp. 1–6 (2014)Google Scholar
  10. 10.
    Hassan, T., Khan, H.A.: Handwritten Bangla numeral recognition using local binary pattern. In: Proceedings of the International Conference on Electrical Engineering and Information Communication Technology, pp. 1–4 (2015)Google Scholar
  11. 11.
    Sarkhel, R., Das, N., Saha, A.K., Nasipuri, M.: A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition. Pattern Recognit. 58, 172–189 (2016)CrossRefGoogle Scholar
  12. 12.
    Singh, P., Verma, A., Chaudhari, N.S.: Feature selection based classifier combination approach for handwritten Devanagari numeral recognition. Sadhana 40(6), 1701–1714 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Prabhanjan, S., Dinesh, R.: Handwritten Devanagari numeral recognition by fusion of classifiers. Int. J. Signal Process. Image Process. Pattern Recognit. 8(7), 41–50 (2015)Google Scholar
  14. 14.
    Roy, K., Pal, T., Pal, U., Kimura, F.: Oriya handwritten numeral recognition system. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 770–774 (2005)Google Scholar
  15. 15.
    Bhowmik, T.K., Parui, S.K., Bhattacharya, U., Shaw, B.: An HMM based recognition scheme for handwritten Oriya numerals. In: Proceedings of the International Conference on Information Technology, pp. 105–110 (2006)Google Scholar
  16. 16.
    Shopon, M., Mohammed, N., Abedin, M.A.: Bangla handwritten digit recognition using autoencoder and deep convolutional neural network. In: Proceedings of the International Workshop on Computational Intelligence, pp. 64–68 (2016)Google Scholar
  17. 17.
    Alom, M.Z., Sidike, P., Taha, T.M., Asari, V.K.: Handwritten Bangla digit recognition using deep learning. arXiv preprint arXiv:1705.02680 (2017)
  18. 18.
    Bhattacharya, U., Chaudhuri, B.B.: Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 444–457 (2009)CrossRefGoogle Scholar
  19. 19.
    Singh, P.K., Sarkar, R., Nasipuri, M.: A study of moment based features on handwritten digit recognition. Appl. Comput. Intell. Soft Comput. 1–17 (2016)CrossRefGoogle Scholar
  20. 20.
    Maitra, D.S., Bhattacharya, U., Parui, S.K.: CNN based common approach to handwritten character recognition of multiple scripts. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1021–1025 (2015)Google Scholar
  21. 21.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  22. 22.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  23. 23.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  24. 24.
    Pramanik, R., Bag, S.: Linear curve fitting-based headline estimation in handwritten words for indian scripts. In: Shankar, B.U., Ghosh, K., Mandal, D.P., Ray, S.S., Zhang, D., Pal, S.K. (eds.) PReMI 2017. LNCS, vol. 10597, pp. 116–123. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-69900-4_15CrossRefGoogle Scholar
  25. 25.
    Bhattacharya, U., Chaudhuri, B.B.: Databases for research on recognition of handwritten characters of Indian scripts. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 789–793 (2005)Google Scholar
  26. 26.
    Das, N., Sarkar, R., Basu, S., Kundu, M., Nasipuri, M., Basu, D.K.: A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application. Appl. Soft Comput. 12(5), 1592–1606 (2012)CrossRefGoogle Scholar
  27. 27.
    Das, N., Reddy, J.M., Sarkar, R., Basu, S., Kundu, M., Nasipuri, M., Basu, D.K.: A statistical-topological feature combination for recognition of handwritten numerals. Appl. Soft Comput. 12(8), 2486–2495 (2012)CrossRefGoogle Scholar
  28. 28.
    Basu, S., Das, N., Sarkar, R., Kundu, M., Nasipuri, M., Basu, D.K.: A novel framework for automatic sorting of postal documents with multi-script address blocks. Pattern Recognit. 43(10), 3507–3521 (2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology (ISM) DhanbadDhanbadIndia

Personalised recommendations