Abstract
In this paper, we investigate the behavior of a MDLSTM-RNN architecture to recognize challenging children handwriting in French language. The system is trained across compositions of synthetic adult handwriting and small collections of real children dictations gathered from first classes elementary school. The paper presents the results of investigations concerning handwriting recognition in a context of weak annotated dataset and synthetic images generation for data augmentation.
Considering very poor databases of children handwriting, we propose series of experiments to show how the model can cope with small quantity of data. In the paper, we show that assuring a controlled variability of words of varying lengths composed by different instances of degraded or poorly-shaped characters, allows a better generalization of the Handwriting Text Recognition (HTR). We also investigate different choices and splitting propositions to compose both training and validation sets, with respect to children styles distributions. The paper presents conclusions of best suited strategies improving HTR accuracies. Compared to performances to train children real data only, the paper illustrates the impact of transfer learning from adults handwriting (from IAM dataset) and the impact of GAN handwriting styles augmentations to improve children handwriting recognition. We show in the paper also that data augmentation through scaling, rotation or even repeating same instances of words allows to enhance performances reaching sometimes human level.
Supported by the Study project founded by the french Auvergne Rhône-Alpes Region.
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
Augustin, E., Brodin, J., Carré, M., Geoffrois, E., Grosicki, E., Prêteux, F.: RIMES evaluation campaign for handwritten mail processing. In: Workshop on Frontiers in Handwriting Recognition, vol. 1, pp. 1–5 (2006)
Axler, G., Wolf, L.: Toward a dataset-agnostic word segmentation method. In: IEEE International Conference on Image Processing, 25th ICIP, pp. 2635–2639 (2018)
Bluche, T., Louradour, J., Messina, R.: Scan, attend and read: end-to-end handwritten paragraph recognition with MDLSTM attention. In: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 1, pp. 1050–1055 (2017). ISSN 15205363, https://doi.org/10.1109/ICDAR.2017.174
Chen, T.W., Chen, Y.L., Chien, S.Y.: Fast image segmentation based on K-means clustering with histograms in HSV color space. In: Proceedings of the 2008 IEEE 10th Workshop on Multimedia Signal Processing. MMSP, pp. 322–325 (2008). https://doi.org/10.1109/MMSP.2008.4665097
Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577–585 (2015). ISSN 10495258
Graves, A.: Generating sequences with recurrent neural networks, pp. 1–43 (2013)
Jia, Y.: Attention mechanism in machine translation. J. Phys. Conf. Seri. JOP 1314(1) (2019). ISSN 17426596, https://doi.org/10.1088/1742-6596/1314/1/012186
Kang, L., Riba, P., Rusiñol, M., Fornés, A., Villegas, M.: Pay attention to what you read: Non-recurrent handwritten text-line recognition. arXiv (2020), ISSN 23318422
Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn. IJDAR 5(1), 39–46 (2003). ISSN 14332833, https://doi.org/10.1007/s100320200071
Matcha, A.C.N.: Nanonets, how to easily do handwriting recognition using deep learning (2020). https://nanonets.com/blog/handwritten-character-recognition/
Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, 2014-December, pp. 285–290 (2014). ISSN 21676453, https://doi.org/10.1109/ICFHR.2014.55
Wernersbach, J., Tracy, C.: East. Swimming Holes Texas, pp. 45–68 (2021). https://doi.org/10.7560/321522-007
Acknowledgements
We warmly acknowledge the Auvergne-Rhône-Alpes Region for supporting the Study project on the Research and Development Booster 2020–2023 Program involving several teams of researchers and industrialists including the two French partner companies AMI and SuperExtraLab.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Medjram, S., Eglin, V., Bres, S. (2022). Challenging Children Handwriting Recognition Study Exploiting Synthetic, Mixed and Real Data. In: Uchida, S., Barney, E., Eglin, V. (eds) Document Analysis Systems. DAS 2022. Lecture Notes in Computer Science, vol 13237. Springer, Cham. https://doi.org/10.1007/978-3-031-06555-2_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-06555-2_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06554-5
Online ISBN: 978-3-031-06555-2
eBook Packages: Computer ScienceComputer Science (R0)
