Advertisement

Towards Accurate Handwritten Word Recognition for Hindi and Bangla

Conference paper
First Online:
Part of the Communications in Computer and Information Science book series (CCIS, volume 841)

Abstract

Building accurate lexicon free handwritten text recognizers for Indic languages is a challenging task, mostly due to the inherent complexities in Indic scripts in addition to the cursive nature of handwriting. In this work, we demonstrate an end-to-end trainable CNN-RNN hybrid architecture which takes inspirations from recent advances of using residual blocks for training convolutional layers, along with the inclusion of spatial transformer layer to learn a model invariant to geometric distortions present in handwriting. In this work we focus building state of the art handwritten word recognizers for two popular Indic scripts – Devanagari and Bangla. To address the need of large scale training data for such low resources languages, we utilize synthetically rendered data for pre-training the network and later fine tune it on the real data. We outperform the previous lexicon based, state of the art methods on the test set of Devanagari and Bangla tracks of RoyDB by a significant margin.

Keywords

Handwriting recognition Lexicon free Indic scripts 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgement

This work was partly supported by IMPRINT scheme, Govt. of India. The authors would also like to thank Oishika, Sounak and Sreya for their help in verifying the results for Bangla.

References

  1. 1.
    Rath, T.M., Manmatha, R.: Word spotting for historical documents. IJDAR 9, 139–152 (2007)CrossRefGoogle Scholar
  2. 2.
    Srihari, S.N., Kuebert, E.J.: Integration of hand-written address interpretation technology into the united states postal service remote computer reader system. In: DAS (1997)Google Scholar
  3. 3.
    Krishnan, P., Jawahar, C.V.: Matching handwritten document images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 766–782. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_46CrossRefGoogle Scholar
  4. 4.
    Milewski, R.J., Govindaraju, V., Bhardwaj, A.: Automatic recognition of handwritten medical forms for search engines. IJDAR 11, 203–218 (2009)CrossRefGoogle Scholar
  5. 5.
    Simons, G.F., Fennig, C.D.: Ethnologue: languages of the world. In: SIL International (2017)Google Scholar
  6. 6.
    Pal, U., Chaudhuri, B.: Indian script character recognition: a survey. PR 37, 1887–1899 (2004)Google Scholar
  7. 7.
    Adak, C., Chaudhuri, B.B., Blumenstein, M.: Offline cursive Bengali word recognition using CNNs with a recurrent model. In: ICFHR (2016)Google Scholar
  8. 8.
    Chaudhuri, B., Pal, U.: A complete printed bangla OCR system. PR 31, 531–549 (1998)Google Scholar
  9. 9.
    Bansal, V., Sinha, R.: A complete OCR for printed hindi text in Devanagari script. In: DAS (2001)Google Scholar
  10. 10.
    Mathew, M., Singh, A.K., Jawahar, C.: Multilingual OCR for Indic scripts. In: DAS (2016)Google Scholar
  11. 11.
    Bhowmik, T.K., Parui, S.K., Roy, U.: Discriminative HMM training with GA for handwritten word recognition. In: ICPR (2008)Google Scholar
  12. 12.
    Bhowmik, T.K., Roy, U., Parui, S.K.: Lexicon reduction technique for bangla handwritten word recognition. In: DAS (2012)Google Scholar
  13. 13.
    Shaw, B., Bhattacharya, U., Parui, S.K.: Combination of features for efficient recognition of offline handwritten Devanagari words. In: ICFHR (2014)Google Scholar
  14. 14.
    Shaw, B., Parui, S.K., Shridhar, M.: Offline handwritten Devanagari word recognition: a holistic approach based on directional chain code feature and HMM. In: ICIT (2008)Google Scholar
  15. 15.
    Roy, P.P., Bhunia, A.K., Das, A., Dey, P., Pal, U.: HMM-based Indic handwritten word recognition using zone segmentation. PR 60, 1057–1075 (2016)Google Scholar
  16. 16.
    Graves, A., Liwicki, M., Fernández, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. PAMI 3, 855–868 (2009)CrossRefGoogle Scholar
  17. 17.
    Garain, U., Mioulet, L., Chaudhuri, B.B., Chatelain, C., Paquet, T.: Unconstrained Bengali handwriting recognition with recurrent models. In: ICDAR (2015)Google Scholar
  18. 18.
    Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: STAR-Net: a spatial attention residue network for scene text recognition. In: BMVC (2016)Google Scholar
  19. 19.
    Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS (2015)Google Scholar
  20. 20.
    Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition (2014)Google Scholar
  21. 21.
    Krishnan, P., Jawahar, C.: Generating synthetic data for text recognition. arXiv preprint arXiv:1608.04224 (2016)
  22. 22.
    Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. PAMI 39, 2298–2304 (2016)CrossRefGoogle Scholar
  23. 23.
    Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR (2016)Google Scholar
  24. 24.
    Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)Google Scholar
  25. 25.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  26. 26.
    Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. IJCV 116, 1–20 (2016)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  28. 28.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: CVPR (2015)Google Scholar
  29. 29.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)Google Scholar
  30. 30.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  31. 31.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_38CrossRefGoogle Scholar
  32. 32.
    Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: ICFHR (2014)Google Scholar
  33. 33.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.CVITIIIT HyderabadHyderabadIndia

Personalised recommendations

Cite paper

Buy options