Skip to main content
SpringerLink
Log in

Offline handwritten Tai Le character recognition using ensemble deep learning

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Handwriting recognition is an important area in pattern recognition. For many years, Tai Le has been widely used in Southwest China and Southeast Asia, which makes it of great interest for recognition research. The characteristics of the highly similar characters in Tai Le, such as its large proportion of similar characters and the randomness of its writing, bring great challenges to the task of recognition. In this paper, a method based on ensemble deep learning for offline handwritten Tai Le characters is proposed. First, the handwritten Tai Le character dataset SDH2019.2 was constructed and preprocessed. Then, an ensemble deep convolutional neural network (EDCNN) model was constructed by using a stacking strategy. Thirty deep neural network (DNN) and logistic regression algorithms were integrated into a strong Tai Le classifier by stacking. Experiments showed that the proposed model is competitive with the base DNN model and other ensemble models. The results indicate that the performance of Tai Le recognition by the stacking ensemble-based deep neural network model is high, with an accuracy of 98.85%. Additionally, its precision, recall and F1-score of 98.87%, 98.85% and 98.85%, respectively, are superior to those of other classic neural network models. To verify the general applicability of EDCNN, its effectiveness was also verified by recognizing MNIST handwritten digits and Devanagari handwritten characters.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Zhang, X., Yin, F., Zhang, Y., Liu, C., Bengio, Y.: Drawing and recognizing Chinese characters with recurrent neural network. IEEE Trans. Pattern Anal. 40(4), 849–862 (2018)

    Article  Google Scholar 

  2. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)

    Article  Google Scholar 

  3. Li, X., Ding, L., Wang, L., Cao, F.: FPGA accelerates deep residual learning for image recognition. In: Proc. IEEE Inf. Technol. Netwo. Electron. Autom. Control Conf. (ITNEC), Chengdu, pp. 837–840 (2017)

  4. Wu, P.J., Meng, X.H., Song, L.: A novel ensemble learning method for crash prediction using road geometric alignments and traffic data. Knowl. Inf. Syst. 12(9), 1128–1146 (2020)

    Google Scholar 

  5. Liu, M., Zhang, L., Li, S.M., et al.: Prediction of herg potassium channel blockage using ensemble learning methods and molecular fingerprints. Toxicol. Lett. 332, 88–96 (2020)

    Article  Google Scholar 

  6. Wang, Y.F., Wang, J.X., Wu, F.X., et al.: AIMAFE: Autism spectrum disorder identification with multi-atlas deep feature representation and ensemble learning. J. Neurosci. Methods 343, 108840 (2020)

    Article  Google Scholar 

  7. Huang, Y.F., Chen, P.H.: Fake news detection using an ensemble learning model based on Self-Adaptive Harmony Search algorithms. Expert Syst. Appl. 159, 113584 (2020)

    Article  Google Scholar 

  8. Krizhevsky, A., Sutskeve, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Commun ACM 25(2), 1097–1105 (2012)

    Google Scholar 

  9. Jain, J., Sahoo, S.K., Prasanna, S.M., Reddy, G.S., et al.: Modified chain code histogram feature for handwritten character recognition. Pattern Recogn, Berlin 84, 611–619 (2012)

    Google Scholar 

  10. Zhang, R., Ding, X.Q., Liu, H.L.: Discriminative training based quadratic classifier for handwritten character recognition. Pattern Recogn. 21(6), 1035–1046 (2007)

    Article  Google Scholar 

  11. He, Z.J., Jin, L.W.: A new fast training algorithm for SVM. In: Proc. Int. Conf. Mach. Learn. Cybern. (ICMLC), Kunming, vol. 6, pp. 3451–3456 (2008)

  12. Ren, H., Wang, W., Liu, C.: Recognizing online handwritten Chinese characters using RNNs with new computing architectures. Pattern Recogn. 93, 179–192 (2019)

    Article  Google Scholar 

  13. Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. 157(10), 3642–3649 (2012)

    Google Scholar 

  14. Cireşan, D., Meier, U.: Multi-column deep neural networks for offline handwritten Chinese character classification. In: Proc. Int. Jt. Conf. Neural Networks, Killarney, vol. 2015, pp. 1–6 (2015)

  15. Zhang, X.Y., Bengio, Y.S., Liu, C.L.: Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark. Pattern Recogn. 61, 348–360 (2017)

    Article  Google Scholar 

  16. Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., Liu, W.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 99, 1–1 (2020)

  17. Kumar Reddy, R.V., Srinivasa Rao, B., Raju, K.P.: Handwritten Hindi digits recognition using convolutional neural network with RMSprop optimization. In: Proc. Int. Conf. Intell. Comput. Control Syst. (ICICCS), Madurai, India, pp. 45–51 (2018)

  18. Saha, C., Faisal, R.H., Rahman, M.M.: Bangla handwritten digit recognition using an improved deep convolutional neural network architecture. In: Int. Conf. Electri., Comput. Commun. Eng. (ECCE), Cox'sBazar, vol 1, pp. 1–6 (2019)

  19. Tan, M., Le, Q.V.: MixConv: mixed depthwise convolutional kernels. Br. Mach. Vis. Conf. arXiv:1907.09595 (2019)

  20. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W. and Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. Workshops, pp. 1571–1580 (2020)

  21. Kaur, R.P., Jindal, M.K., Kumar, M.: Text and graphics segmentation of newspapers printed in Gurmukhi script: a hybrid approach. Vis. Comput. 37, 1637–1659 (2020)

  22. Inunganbi, S., Choudhary, P., Manglem, K.: Meitei Mayek handwritten dataset: compilation, segmentation, and character recognition. Vis. Comput. 30(10), 1–15 (2020)

    Google Scholar 

  23. Zhu, H., Lu, J., Cai, J., Zheng, J., Lu, S., Thalmann, N.M.: Multiple human identification and cosegmentation: a human-oriented CRF approach with poselets. IEEE Trans. Multimed. 18(8), 1516–1530 (2016)

    Article  Google Scholar 

  24. Sun, S.L., Wang, S.Y., Wei, Y.J.: A new ensemble deep learning approach for exchange rates forecasting and trading. Adv. Eng. Inf. 46, 101160 (2020)

    Article  Google Scholar 

  25. Shan, S., Cao, B., Wu, Z.: Forecasting the short-term electricity consumption of building using a novel ensemble model. IEEE Access 7, 88093–88106 (2019)

    Article  Google Scholar 

  26. An, N., Ding, H.T., Yang, J.Y., Au, R., Ting Ang, F.A.: Deep ensemble learning for Alzheimer’s disease classification. J. Biomed. Inf. 105, 103411 (2020)

    Article  Google Scholar 

  27. Kemal, A.: Stacking ensemble based deep neural networks modeling for effective epileptic seizure detection. Expert Syst. Appl. 148, 113239 (2020)

    Article  Google Scholar 

  28. Han, J., Lu, C.H., Cao, Z.M., Mu, H.W.: Integration of deep neural networks and ensemble learning machines for missing well logs estimation. Flow Meas. Instrum. 73, 101748 (2020)

    Article  Google Scholar 

  29. Li, Z.X., Wu, D.Z., Hu, C., Terpenny, J.: An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction. Reliab. Eng. Syst. Saf. 184, 110–122 (2019)

    Article  Google Scholar 

  30. Alizadehashraf, B., Roohi, S.: Persian handwritten character recognition using convolutional neural network. Iran. Conf. Electr. Eng. (ICEE), Iran 22–23, 247–251 (2017)

    Google Scholar 

  31. Sarkhel, R., Das, N., et al.: A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition. Pattern Recogn 58, 172–189 (2016)

    Article  Google Scholar 

  32. Sarkhel, R., Saha, A.K., Das, N.: An enhanced harmony search method for Bangla handwritten character recognition using region sampling. In: Proc. Int. Conf. Infor. Syst. (ReTIS), pp. 325–330 (2015)

  33. Gupta, A., Sarkhel, R., Das, N., Kundu, M.: Multiobjective optimization for recognition of isolated handwritten Indic scripts. Pattern Recogn. Lett. 128, 318–325 (2019)

    Article  Google Scholar 

  34. Sarkhel, R., Das, N., Das, A., et al.: A multi-scale deep quad tree-based feature extraction method for the recognition of isolated handwritten characters of popular indic scripts. Pattern Recogn. 71, 78–93 (2017)

    Article  Google Scholar 

  35. Xu, X., Xu, S., Jin, L., et al.: Characteristic analysis of Otsu threshold and its applications. Pattern Recogn. Lett. 32(7), 956–961 (2011)

    Article  Google Scholar 

  36. Xu, Z., Hong, Z., Zhang, Y., Wu, J., Tsoi, A.C., Tao, D.: Multinomial latent logistic regression for image understanding. IEEE Trans Image Process 25(2), 973–987 (2016)

    Article  MathSciNet  MATH  Google Scholar 

  37. Khan, M.A., Sharif, M., Javed, M.Y., Akram, T., Yasmin, M., Saba, T.: License number plate recognition system using entropy-based features selection approach with SVM. IET Image Process. 12(2), 200–209 (2018)

    Article  Google Scholar 

  38. Xu, C., et al.: Multi-loss regularized deep neural network. IEEE Trans Circuits Syst Video Technol 26(12), 2273–2283 (2016)

    Article  Google Scholar 

  39. Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. Int. Conf. Learn. Represent, ICLR—Conf. Track Proc. 1, 149801 (2015)

    Google Scholar 

  40. Chan, T.H., Jia, K., Gao, S., et al.: PCANet: a simple deep learning baseline for image classification. IEEE Trans. Image Process. 24(12), 5017–5032 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  41. Xu, C., Lu, C., Liang, X., et al.: Multi-loss regularized deep neural network. IEEE Trans. Circuits Syst. Video Technol. 26(12), 2273–2283 (2016)

    Article  Google Scholar 

  42. Acharya, S., Pant, A.K., Gyawali, P.K.: Deep learning based large scale handwritten Devanagari character recognition. SKIMA—Int. Conf. Softw., Knowl., Inf. Manag. Appl., Kathmandu 740041, 1–6 (2015)

    Google Scholar 

  43. Gharde, S.S., Ramteke, R.J., Kotkar, V.A., Bage, D.D.: Handwritten Devanagari numeral and vowel recognition using invariant moments. Proc. Int. Conf. Glob. Trends Sig. 1, 255–260 (2016)

    Google Scholar 

  44. Deore, S.P., Pravin, A.: Devanagari handwritten character recognition using fine-tuned deep convolutional neural network on trivial dataset. SADHANA-ACAD P ENG S 45(243), 2–13 (2020)

    Google Scholar 

  45. Ghosh, R., Vamshi, C., Kumar, P.: RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning. Pattern Recogn. 92, 203–218 (2019)

    Article  Google Scholar 

Download references

Acknowledgements

This research was supported by the National Language Commission research project (No. YB135-116), and all support is gratefully acknowledged.

Author information

Authors and Affiliations

  1. SEAC Key Laboratory of Big Data Applied Technology, Dalian Minzu University, Dalian, 116600, China

    Hai Guo, Yifan Liu, Doudou Yang & Jingying Zhao

  2. Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, 116024, China

    Jingying Zhao

Authors
  1. Hai Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yifan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Doudou Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jingying Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hai Guo.

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

Guo, H., Liu, Y., Yang, D. et al. Offline handwritten Tai Le character recognition using ensemble deep learning. Vis Comput 38, 3897–3910 (2022). https://doi.org/10.1007/s00371-021-02230-2

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-021-02230-2

Keywords

Search

Navigation