Skip to main content

Handwritten Digit Recognition Using Bayesian ResNet


The problem of handwritten digit recognition has seen various developments in the recent times, especially in neural network domain. The methods based on neural network work quite effectively for the seen classes of data by providing deterministic results. However, these methods tend to behave in similar fashion even for unseen class of data. For example, a neural network trained on English language digits will give a deterministic prediction even when tested on digits of other languages. Hence, it is required to predict uncertainty for such methods in this scenario. In this paper, we employ Bayesian inference into the existing ResNet18 framework to bring out uncertainty for handwritten digit recognition when there is a new class of test digit. We term the new architecture as B-ResNet. The novel B-ResNet is first of its kind to be investigated for the handwritten digit recognition. Various experiments on datasets of English, Devanagari, Gujarati, Bengali digits and their all possible combinations demonstrate the efficiency and performance of the B-ResNet for hand written digit recognition.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  1. Baheti MJ, Kale KV, Jadhav ME. Comparison of classifiers for gujarati numeral recognition. 2011.

  2. Bajaj R, Dey L, Chaudhury S. Devnagari numeral recognition by combining decision of multiple connectionist classifiers. Sadhana. 2002;27(1):59–72.

    Article  Google Scholar 

  3. Basu S, Sarkar R, Das N, Kundu M, Nasipuri M, Basu DK. A fuzzy technique for segmentation of handwritten bangla word images. In: 2007 international conference on computing: theory and applications (ICCTA’07), pp. 427–433, IEEE. 2007.

  4. Bhattacharya U, Chaudhuri B. Databases for research on recognition of handwritten characters of indian scripts. In: Eighth international conference on document analysis and recognition (ICDAR’05), pp. 789–793, IEEE. 2005.

  5. Bhattacharya U, Chaudhuri BB. Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Anal Mach Intell. 2008;31(3):444–57.

    Article  Google Scholar 

  6. Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D. Weight uncertainty in neural networks. 2015. arXiv:1505.05424.

  7. Bojarski M, Del Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang J, et al. End to end learning for self-driving cars. 2016. arXiv:1604.07316.

  8. Buntine WL, Weigend AS. Bayesian back-propagation. Compl Syst. 1991;5(6):603–43.

    MATH  Google Scholar 

  9. Chowdhury RR, Hossain MS, ul Islam R, Andersson K, Hossain S. Bangla handwritten character recognition using convolutional neural network with data augmentation. In: 2019 Joint 8th international conference on informatics, electronics & vision (ICIEV) and 2019 3rd international conference on imaging, vision & pattern recognition (icIVPR), pp. 318–323, IEEE. 2019.

  10. Cireşan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification. 2012. arXiv:1202.2745.

  11. Cireşan DC, Meier U, Gambardella LM, Schmidhuber J. Deep, big, simple neural nets for handwritten digit recognition. Neural Comput. 2010;22(12):3207–20.

    Article  Google Scholar 

  12. Connell SD, Jain AK. Template-based online character recognition. Pattern Recogn. 2001;34(1):1–14.

    Article  Google Scholar 

  13. Deng L, Yu D. Deep convex net: a scalable architecture for speech pattern classification. In: twelfth annual conference of the international speech communication association. 2011.

  14. Der Kiureghian A, Ditlevsen O. Aleatory or epistemic? Does it matter? Struct Saf. 2009;31(2):105–12.

    Article  Google Scholar 

  15. Desai AA. Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recogn. 2010;43(7):2582–9.

    Article  Google Scholar 

  16. Gal Y, Ghahramani Z. Dropout as a bayesian approximation: Insights and applications. In: deep learning workshop, ICML, vol. 1, p. 2. 2015.

  17. Goswami MM, Mitra SK. Offline handwritten gujarati numeral recognition using low-level strokes. Int J Appl Pattern Recogn. 2015;2(4):353–79.

    Article  Google Scholar 

  18. Graves A. Practical variational inference for neural networks. In: Advances in neural information processing systems, pp. 2348–2356. 2011.

  19. Han Z, Liu CP, Yin XC. A two-stage handwritten character segmentation approach in mail address recognition. In: Eighth international conference on document analysis and recognition (ICDAR’05), pp. 111–115, IEEE. 2005.

  20. Hanmandlu M, Murthy OR. Fuzzy model based recognition of handwritten numerals. Pattern Recogn. 2007;40(6):1840–54.

    Article  Google Scholar 

  21. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778. 2016.

  22. Hoque MM, Karim MR, Hossain MG, Arefin MS, Monjur-Ul-Hasan M. Bangla numeral recognition engine (bnre). In: 2008 international conference on electrical and computer engineering, pp. 644–647, IEEE. 2008.

  23. Jayadevan R, Kolhe SR, Patil PM, Pal U. Automatic processing of handwritten bank cheque images: a survey. Int J Doc Anal Recogn. 2012;15(4):267–96.

    Article  Google Scholar 

  24. Kendall A, Gal Y. What uncertainties do we need in bayesian deep learning for computer vision? 2017. arXiv:1703.04977.

  25. Keysers D, Deselaers T, Gollan C, Ney H. Deformation models for image recognition. IEEE Trans Pattern Anal Mach Intell. 2007;29(8):1422–35.

    Article  Google Scholar 

  26. Kingma DP, Salimans T, Welling M. Variational dropout and the local reparameterization trick. In: Advances in neural information processing systems, pp. 2575–2583. 2015.

  27. Kumar P, Sharma N, Rana A. Handwritten character recognition using different kernel based svm classifier and mlp neural network (a comparison). Int J Comput Appl. 2012;53:11.

  28. LeCun Y, Bottou L, Bengio Y, Haffner P, et al. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278–324.

    Article  Google Scholar 

  29. LeCun Y, Cortes C. MNIST handwritten digit database. 2010.

  30. MacKay DJ. Probable networks and plausible predictions–a review of practical bayesian methods for supervised neural networks. Netw Comput Neural Syst. 1995;6(3):469–505

  31. Meier U, Ciresan DC, Gambardella LM, Schmidhuber J. Better digit recognition with a committee of simple neural nets. In: 2011 international conference on document analysis and recognition, pp. 1250–1254, IEEE. 2011.

  32. Moutarde F, Bargeton A, Herbin A, Chanussot L. Robust on-vehicle real-time visual detection of american and european speed limit signs, with a modular traffic signs recognition system. In: 2007 IEEE intelligent vehicles symposium, pp. 1122–1126, IEEE. 2007.

  33. Nagar R, Mitra SK. Feature extraction based on stroke orientation estimation technique for handwritten numeral. In: 2015 eighth international conference on advances in pattern recognition (ICAPR), pp. 1–6, IEEE. 2015.

  34. Neal RM. Bayesian learning for neural networks, vol. 118. Berlin:Springer Science & Business Media; 2012.

  35. Niu XX, Suen CY. A novel hybrid cnn-svm classifier for recognizing handwritten digits. Pattern Recogn. 2012;45(4):1318–25.

    Article  Google Scholar 

  36. Pal U, Wakabayashi T, Kimura F. Handwritten numeral recognition of six popular scripts, ninth international conference on document analysis and recognition icdar 07. 2007.

  37. Palvanov A, Im Cho Y. Comparisons of deep learning algorithms for mnist in real-time environment. Int J Fuzzy Logic Intell Syst. 2018;18(2):126–34.

    Article  Google Scholar 

  38. Prasad JR, Kulkarni U, Prasad RS. Offline handwritten character recognition of gujrati script using pattern matching. In: 2009 3rd international conference on anti-counterfeiting, security, and identification in communication, pp. 611–615, IEEE. 2009.

  39. Saha C, Faisal RH, Rahman MM. Bangla handwritten digit recognition using an improved deep convolutional neural network architecture. In: 2019 international conference on electrical, computer and communication engineering (ECCE), pp. 1–6, IEEE. 2019.

  40. Shridhar K, Laumann F, Liwicki M. Uncertainty estimations by softplus normalization in bayesian convolutional neural networks with variational inference. 2018. arXiv:1806.05978.

  41. Shridhar K, Laumann F, Liwicki M. A comprehensive guide to bayesian convolutional neural network with variational inference. 2019. arXiv:1901.02731.

Download references


This work has not been funded by any agency.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Purva Mhasakar.

Ethics declarations

Conflicts of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mhasakar, P., Trivedi, P., Mandal, S. et al. Handwritten Digit Recognition Using Bayesian ResNet. SN COMPUT. SCI. 2, 399 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: