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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rath, T.M., Manmatha, R.: Word spotting for historical documents. IJDAR 9, 139–152 (2007)
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)
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_46
Milewski, R.J., Govindaraju, V., Bhardwaj, A.: Automatic recognition of handwritten medical forms for search engines. IJDAR 11, 203–218 (2009)
Simons, G.F., Fennig, C.D.: Ethnologue: languages of the world. In: SIL International (2017)
Pal, U., Chaudhuri, B.: Indian script character recognition: a survey. PR 37, 1887–1899 (2004)
Adak, C., Chaudhuri, B.B., Blumenstein, M.: Offline cursive Bengali word recognition using CNNs with a recurrent model. In: ICFHR (2016)
Chaudhuri, B., Pal, U.: A complete printed bangla OCR system. PR 31, 531–549 (1998)
Bansal, V., Sinha, R.: A complete OCR for printed hindi text in Devanagari script. In: DAS (2001)
Mathew, M., Singh, A.K., Jawahar, C.: Multilingual OCR for Indic scripts. In: DAS (2016)
Bhowmik, T.K., Parui, S.K., Roy, U.: Discriminative HMM training with GA for handwritten word recognition. In: ICPR (2008)
Bhowmik, T.K., Roy, U., Parui, S.K.: Lexicon reduction technique for bangla handwritten word recognition. In: DAS (2012)
Shaw, B., Bhattacharya, U., Parui, S.K.: Combination of features for efficient recognition of offline handwritten Devanagari words. In: ICFHR (2014)
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)
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)
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)
Garain, U., Mioulet, L., Chaudhuri, B.B., Chatelain, C., Paquet, T.: Unconstrained Bengali handwriting recognition with recurrent models. In: ICDAR (2015)
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)
Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NIPS (2015)
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition (2014)
Krishnan, P., Jawahar, C.: Generating synthetic data for text recognition. arXiv preprint arXiv:1608.04224 (2016)
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)
Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR (2016)
Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. IJCV 116, 1–20 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
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)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
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_38
Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: ICFHR (2014)
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
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.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.V. (2018). Towards Accurate Handwritten Word Recognition for Hindi and Bangla. In: Rameshan, R., Arora, C., Dutta Roy, S. (eds) Computer Vision, Pattern Recognition, Image Processing, and Graphics. NCVPRIPG 2017. Communications in Computer and Information Science, vol 841. Springer, Singapore. https://doi.org/10.1007/978-981-13-0020-2_41
Download citation
DOI: https://doi.org/10.1007/978-981-13-0020-2_41
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-0019-6
Online ISBN: 978-981-13-0020-2
eBook Packages: Computer ScienceComputer Science (R0)