TabbyPDF: Web-Based System for PDF Table Extraction
- 3 Citations
- 724 Downloads
Abstract
PDF is one of the most widespread ways to represent non-editable documents. Many of PDF documents are machine-readable but remain untagged. They have no tags for identifying layout items such as paragraphs, columns, or tables. One of the important challenges with these documents is how to extract tabular data from them. The paper presents a novel web-based system for extracting tables located in untagged PDF documents with a complex layout, for recovering their cell structures, and for exporting them into a tagged form (e.g. in CSV or HTML format). The system uses a heuristic-based approach to table detection and structure recognition. It mainly relies on recovering a human reading order of text, including document paragraphs and table cells. A prototype of the system was evaluated, using the methodology and dataset of “ICDAR 2013 Table Competition”. The standard metric F-score is 93.64% for the structure recognition phase and 83.18% for the table extraction with automatic table detection. The results are comparable with the state-of-the-art academic solutions.
Keywords
Table understanding Table extraction Table detection Table recognition Document analysis PDF accessibilityNotes
Acknowledgments
This work is supported by the Russian Foundation for Basic Research (grants 18-07-00758 and 17-47-380007). The prototype of TabbyPDF is deployed on resources of the Shared Equipment Center of Integrated Information and Computing Network for Irkutsk Research and Educational Complex (http://net.icc.ru).
References
- 1.Burdick, D., et al.: Financial analytics from public data. In: Proceedings of the International Workshop on Data Science for Macro-Modeling, DSMM 2014, pp. 4:1–4:6 (2014). https://doi.org/10.1145/2630729.2630742
- 2.Corrêa, A.S., Zander, P.O.: Unleashing tabular content to open data: a survey on PDF table extraction methods and tools. In: Proceedings of 18th International Conference on Digital Government Research, pp. 54–63 (2017). https://doi.org/10.1145/3085228.3085278
- 3.Coüasnon, B., Lemaitre, A.: Recognition of tables and forms. In: Handbook of Document Image Processing and Recognition, pp. 647–677 (2014). https://doi.org/10.1007/978-0-85729-859-1_20CrossRefGoogle Scholar
- 4.Göbel, M., Hassan, T., Oro, E., Orsi, G.: ICDAR 2013 table competition. In: Proceedings of 12th International Conference on Document Analysis and Recognition, pp. 1449–1453 (2013)Google Scholar
- 5.Göbel, M., Hassan, T., Oro, E., Orsi, G.: A methodology for evaluating algorithms for table understanding in PDF documents. In: Proceedings of 2012 ACM Symposium on Document Engineering, pp. 45–48 (2012). https://doi.org/10.1145/2361354.2361365
- 6.Göbel, M., Hassan, T., Oro, E., Orsi, G., Rastan, R.: Table modelling, extraction and processing. In: Proceedings of 2016 ACM Symposium on Document Engineering, pp. 1–2 (2016). https://doi.org/10.1145/2960811.2967173
- 7.Govindaraju, V., Zhang, C., Ré, C.: Understanding tables in context using standard NLP toolkits. In: Proceedings of 51st Annual Meeting of the Association for Computational Linguistics, pp. 658–664 (2013)Google Scholar
- 8.Hassan, T., Baumgartner, R.: Table recognition and understanding from PDF files. In: Proceedings of 9th International Conference on Document Analysis and Recognition, vol. 02, pp. 1143–1147 (2007). http://dl.acm.org/citation.cfm?id=1304596.1304833
- 9.Hu, J., Liu, Y.: Analysis of documents born digital. In: Doermann, D., Tombre, K. (eds.) Handbook of Document Image Processing and Recognition, pp. 775–804. Springer, London (2014). https://doi.org/10.1007/978-0-85729-859-1_26CrossRefGoogle Scholar
- 10.Khusro, S., Latif, A., Ullah, I.: On methods and tools of table detection, extraction and annotation in PDF documents. J. Inf. Sci. 41(1), 41–57 (2015). https://doi.org/10.1177/0165551514551903CrossRefGoogle Scholar
- 11.Liu, Y., Bai, K., Mitra, P., Giles, C.L.: TableSeer: automatic table metadata extraction and searching in digital libraries. In: Proceedings of 7th ACM/IEEE Joint Conference on Digital Libraries, pp. 91–100 (2007). https://doi.org/10.1145/1255175.1255193
- 12.Nganji, J.T.: The portable document format (PDF) accessibility practice of four journal publishers. Libr. Inf. Sci. Res. 37, 254–262 (2015). http://www.sciencedirect.com/science/article/pii/S0740818815000134CrossRefGoogle Scholar
- 13.Nurminen, A.: Algorithmic extraction of data in tables in PDF documents. Master’s thesis, Tampere University of Technology, Tampere, Finland (2013)Google Scholar
- 14.Oro, E., Ruffolo, M.: PDF-TREX: an approach for recognizing and extracting tables from PDF documents. In: Proceedings of 10th International Conference on Document Analysis and Recognition, pp. 906–910 (2009)Google Scholar
- 15.Perez-Arriaga, M.O., Estrada, T., Abad-Mota, S.: TAO: system for table detection and extraction from PDF documents. In: Proceedings of 29th International Florida Artificial Intelligence Research Society Conference, pp. 591–596 (2016)Google Scholar
- 16.Ramel, J.Y., Crucianu, M., Vincent, N., Faure, C.: Detection, extraction and representation of tables. In: Proceedings of 7th International Conference on Document Analysis and Recognition, vol. 1, pp. 374–378 (2003)Google Scholar
- 17.Rastan, R., Paik, H.Y., Shepherd, J.: TEXUS: a task-based approach for table extraction and understanding. In: Proceedings of 2015 ACM Symposium on Document Engineering, pp. 25–34 (2015). https://doi.org/10.1145/2682571.2797069
- 18.Rastan, R., Paik, H.Y., Shepherd, J.: A PDF wrapper for table processing. In: Proceedings of 2016 ACM Symposium on Document Engineering, pp. 115–118 (2016). https://doi.org/10.1145/2960811.2967162
- 19.Sabol, V., Tschinkel, G., Veas, E., Hoefler, P., Mutlu, B., Granitzer, M.: Discovery and visual analysis of linked data for humans. In: Mika, P., et al. (eds.) ISWC 2014. LNCS, vol. 8796, pp. 309–324. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11964-9_20CrossRefGoogle Scholar
- 20.Shigarov, A., Bychkov, I., Ruzhnikov, G., Khmel’nov, A.: A method of table detection in metafiles. Pattern Recognit. Image Anal. 19(4), 693–697 (2009). https://doi.org/10.1134/S1054661809040191CrossRefzbMATHGoogle Scholar
- 21.Shigarov, A.: Table understanding using a rule engine. Expert. Syst. Appl. 42(2), 929–937 (2015)CrossRefGoogle Scholar
- 22.Shigarov, A., Fedorov, R.: Simple algorithm page layout analysis. Pattern Recognit. Image Anal. 21(2), 324–327 (2011). https://doi.org/10.1134/S1054661811021008CrossRefGoogle Scholar
- 23.Shigarov, A., Mikhailov, A., Altaev, A.: Configurable table structure recognition in untagged PDF documents. In: Proceedings of 2016 ACM Symposium on Document Engineering, pp. 119–122 (2016). https://doi.org/10.1145/2960811.2967152
- 24.Shigarov, A.O., Mikhailov, A.A.: Rule-based spreadsheet data transformation from arbitrary to relational tables. Inf. Syst. 71, 123–136 (2017). https://doi.org/10.1016/j.is.2017.08.004CrossRefGoogle Scholar
- 25.e Silva, A.C.: Parts that add up to a whole: a framework for the analysis of tables. Ph.D. thesis, University of Edinburgh, Tampere, Finland (2010)Google Scholar
- 26.e Silva, A.C., Jorge, A.M., Torgo, L.: Design of an end-to-end method to extract information from tables. Int. J. Doc. Anal. Recognit. (IJDAR) 8(2), 144–171 (2006)CrossRefGoogle Scholar
- 27.Yildiz, B., Kaiser, K., Miksch, S.: pdf2table: a method to extract table information from PDF files. In: Proceedings of 2nd Indian International Conference on Artificial Intelligence, Pune, India, pp. 1773–1785 (2005)Google Scholar