Abstract
This paper presents a method for character semantic segmentation in full-text documents from post World War II Czechoslovakia. Unfortunately, standard optical character recognition algorithms have problems to accurately read these documents due to their noisy nature. Therefore we were looking for some ways to improve these unsatisfactory results. Our approach is based on fully-convolutional neural network inspired by U-Net architecture. We are utilizing a synthetic image generator for obtaining a training set for our method. We reached 99.53% recognition accuracy for synthetic data. For real data, we are providing qualitative results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bureš, L., Neduchal, P., Hlaváč, M., Hrúz, M.: Generation of synthetic images of full-text documents. In: Proceedings Speech and Computer, pp. 68–75 (2018)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1520–1528 (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–341 (2015)
Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017)
Hajic, J., Dorfer, M., Widmer, G., Pecina, P.: Towards full-pipeline handwritten OMR with musical symbol detection by U-Nets. In: Proceedings of the 19th International Society for Music Information Retrieval Conference, pp. 23–27 (2018)
Smith, R.: An overview of the Tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 629–633 (2007)
Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 512–528. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_34
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. Int. J. Comput. Vision 116(1), 1–20 (2016)
Larsen, A.B.L., Sønderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, ICML vol. 48, pp. 1558–1566 (2016)
Tokui, S., Oono, K., Hido, S., Clayton, J.: Chainer: a next-generation open source framework for deep learning. In: Proceedings of Workshop on Machine Learning Systems(LearningSys) in The Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS) (2015)
Akiba, T., Fukuda, K., Suzuki, S.: ChainerMN: scalable distributed deep learning framework. In: Proceedings of Workshop on ML Systems in The Thirty-First Annual Conference on Neural Information Processing Systems (NIPS) (2017)
Acknowledgments
This research was supported by the Ministry of Culture of the Czech Republic, project No. DG16P02B048. Access to computing and storage facilities owned by parties and projects contributing to the National Grid Infrastructure MetaCentrum provided under the programme “Projects of Large Research, Development, and Innovations Infrastructures” (CESNET LM2015042), is greatly appreciated.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gruber, I., Hlaváč, M., Hrúz, M., Železný, M. (2019). Semantic Segmentation of Historical Documents via Fully-Convolutional Neural Network. In: Salah, A., Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2019. Lecture Notes in Computer Science(), vol 11658. Springer, Cham. https://doi.org/10.1007/978-3-030-26061-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-26061-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26060-6
Online ISBN: 978-3-030-26061-3
eBook Packages: Computer ScienceComputer Science (R0)