Abstract
This paper proposes an end-to-end table structure analysis method using graph attention networks (GATs) that includes table detection. The proposed method initially identifies tables within documents, estimates whether horizontally adjacent tokens within the table belong to the same cell using GATs, subsequently estimates implicitly ruled lines required for cell separation but not actually drawn, and finally merges the remaining tokens to estimate cells, again using GATs. We have also collected 800 new tables and annotated them with structural information to augment the training data for the proposed method. Evaluation experiments showed that the proposed method achieved an F-measure of 0.984, outperforming other methods including the commercial ABBYY FineReader PDF in accuracy of table structure analysis with table detection. This paper also showed that the 800 newly annotated tables enhanced the proposed method’s accuracy.
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
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
- 9.
References
Aoyagi, H., Kanazawa, T., Takasu, A., Uwano, F., Ohta, M.: Table-structure recognition method consisting of plural neural network modules. In: Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, pp. 542–549 (2022)
Batista, G.E.A.P.A., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor. Newsl. 6(1), 20–29 (2004)
Chi, Z., Huang, H., Xu, H.D., Yu, H., Yin, W., Mao, X.L.: Complicated table structure recognition. arXiv:1908.04729 (2019)
Gao, L., et al.: ICDAR 2019 competition on table detection and recognition (cTDaR). In: Proceedings of the 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1510–1515 (2019)
Göbel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1449–1453 (2013)
Göbel, M., Hassan, T., Oro, E., Orsi, G.: A methodology for evaluating algorithms for table understanding in pdf documents. In: Proceedings of the 2012 ACM Symposium on Document Engineering, pp. 45–48 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR) (2015)
Kuhar, M., Merčun, T.: Exploring user experience in digital libraries through questionnaire and eye-tracking data. Libr. Inf. Sci. Res. 44(3), 101175 (2022)
Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: table benchmark for image-based table detection and recognition. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1918–1925 (2020)
Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. arXiv:1301.3781 (2013)
Ohta, M., Yamada, R., Kanazawa, T., Takasu, A.: Table-structure recognition method using neural networks for implicit ruled line estimation and cell estimation. In: Proceedings of the 21st ACM Symposium on Document Engineering (2021)
Prasad, D., Gadpal, A., Kapadni, K., Visave, M., Sultanpure, K.: CascadeTabNet: an approach for end to end table detection and structure recognition from image-based documents. In: Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2439–2447 (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: Proceedings of International Conference on Learning Representations (2018)
Yamada, R., Ohta, M., Takasu, A.: An automatic graph generation method for scholarly papers based on table structure analysis. In: Proceedings of the 10th International Conference on Management of Digital EcoSystems, pp. 132–140 (2018)
Zheng, X., Burdick, D., Popa, L., Zhong, X., Wang, N.X.R.: Global table extractor (GTE): a framework for joint table identification and cell structure recognition using visual context. In: Proceedings of 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 697–706 (2021)
Zhong, X., ShafieiBavani, E., Jimeno Yepes, A.: Image-based table recognition: data, model, and evaluation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 564–580. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_34
Acknowledgements
This work was supported by JSPS KAKENHI Grant Number JP22H03904 and ROIS NII Open Collaborative Research 2023 (23FC02).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ohta, M., Aoyagi, H., Uwano, F., Kanazawa, T., Takasu, A. (2023). An End-to-End Table Structure Analysis Method Using Graph Attention Networks. In: Goh, D.H., Chen, SJ., Tuarob, S. (eds) Leveraging Generative Intelligence in Digital Libraries: Towards Human-Machine Collaboration. ICADL 2023. Lecture Notes in Computer Science, vol 14458. Springer, Singapore. https://doi.org/10.1007/978-981-99-8088-8_20
Download citation
DOI: https://doi.org/10.1007/978-981-99-8088-8_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8087-1
Online ISBN: 978-981-99-8088-8
eBook Packages: Computer ScienceComputer Science (R0)