Table Recognition Technology in Tax Documents of the Russian Federation

This paper investigates the problem of cell recognition in the image of a table using the example of the Russian tax document (2-NDFL). Despite the simple structure of the tables, the printing method is based on a flexible template. The flexibility of the form is observed in the modifications of textual information and in the table area. The flexibility of tables lies in the modification of the number and size of columns. A structural method was proposed for table detection. The input data are the detected horizontal and vertical segments. Segments were searched by the Smart Document Reader system. Implementing and testing the method were also carried out in the Smart Document Reader system. In addition to detecting the area where tables can be placed, the following objectives were achieved: searching for table cells, naming table cells, and validating the table area. Validation of the table area was performed for separate tables and for table sets. The application of table aggregate descriptions showed the high reliability of linking table sets.

Keywords

table recognition; line detection; table layout.

References

1. Vasiliev S.S., Korobkin D.M., Kravets A.G., Fomenkov S.A., Kolesnikov S.G. Extraction of Cyber-Physical Systems Inventions Structural Elements Of Russian-Language Patents. Cyber-Physical Systems: Advances in Design and Modelling. Studies in Systems, Decision and Control, 2020, vol. 259, pp. 55-68. DOI: 10.1007/978-3-030-32579-4_5
2. Slavin O., Arlazarov V., Tarkhanov I. Models and Methods Flexible Documents Matching Based on the Recognized Words. Cyber-Physical Systems: Advances in Design and Modelling. Studies in Systems, Decision and Control. Springer Nature Switzerland AG, 2021, vol. 350, pp. 173-184. DOI: 10.1007/978-3-030-67892-0_15
3. Varma O., Srivastava S., Gayathri M. Technical Invoice Data Extraction System: State of the Art, Research Challenges and Countermeasures. Ambient Communications and Computer Systems. Lecture Notes in Networks and Systems, 2022, vol. 356, pp. 201-210. DOI: 10.1007/978-981-16-7952-0_19
4. Pegu B., Singh M., Agarwal A., Mitra A., Singh K. Table Structure Recognition Using CoDec Encoder-Decoder. Document Analysis and Recognition - ICDAR 2021 Workshops. Lecture Notes in Computer Science, Lausanne, 2021, vol. 12917, pp. 66-80. DOI: 10.1007/978-3-030-86159-9_5
5. Siddiqui S.A., Khan P.I., Dengel A., Ahmed S. Rethinking Semantic Segmentation for Table Structure Recognition in Documents. Proceedings of the International Conference on Document Analysis and Recognition, Sydney, 2019, pp. 1397-1402. DOI: 10.1109/ICDAR.2019.00225
6. Gilani A., Qasim S.R., Malik I., Shafait F. Table Detection using Deep Learning. Proceedings of the International Conference on Document Analysis and Recognition, Kyoto, 2017, pp. 771-776. DOI: 10.1109/ICDAR.2017.131
7. Gatos B., Danatsas D., Pratikakis I., Perantonis S.J. Automatic table detection in document images. Pattern Recognition and Data Mining, Third International Conference on Advances in Pattern Recognition, Bath, 2005, vol. 3686, pp. 609-618. DOI: 10.1007/11551188_67
8. Siddiqui S.A., Malik M.I., Agne S., Dengel A., Ahmed S. DeCNT: Deep Deformable CNN for Table Detection. A Multidisciplinary Open Access Journal, 2018, vol. 6, pp. 74151-74161, DOI: 10.1109/ACCESS.2018.2880211
9. 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. Conference on Computer Vision and Pattern Recognition Workshops, Seattle, 2020, pp. 572-573. DOI: 10.1109/CVPRW50498.2020.00294
10. Gobel M., Hassan T., Oro E., Orsi G. ICDAR 2013 Table Competition. Proceedings of the International Conference on Document Analysis and Recognition, Washington, 2013, pp. 1449-1453. DOI: 10.1109/ICDAR.2013.292
11. Qiao Liang, Li Zaisheng, Cheng Zhanzhan, et al. LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment. Document Analysis and Recognition, 2021, article ID: 12821. DOI: 10.1007/978-3-030-86549-8_7
12. Liu Ying, Bai K., Mitra P., Giles C.L. Improving the Table Boundary Detection in PDFs by Fixing the Sequence Error of the Sparse Lines. International Conference on Document Analysis and Recognition, Barcelona, 2009, pp. 1006-1010. DOI: 10.1109/ICDAR.2009.138
13. Liu Ying., Mitra P., Giles C.L. Identifying Table Boundaries in Digital Documents via Sparse Line Detection. Proceedings of the Conference on Information and Knowledge Management, Napa Valley, 2008, pp. 1311-1320. DOI: 10.1145/1458082.1458255
14. Paliwal S.S., Vishwanath D., Rahul R., Sharma M., Vig L. Tablenet: Deep Learning Model for End-To-End Table Detection and Tabular Data Extraction from Scanned Document Images. International Conference on Document Analysis and Recognition, 2020, pp. 128-133. DOI: 10.1109/ICDAR.2019.00029
15. Schreiber S., Agne S., Wolf I., Dengel A., Ahmed S. Deepdesrt: Deep Learning for De-Tection and Structure Recognition of Tables in Document Images. International Conference on Document Analysis and Recognition, Kyoto, 2017, pp. 1162-1167. DOI: 10.1109/ICDAR.2017.192
16. Siddiqui S.A., Fateh I.A., Rizvi S.T.R., Dengel A., Ahmed S. Deeptabstr: Deep Learning Based Table Structure Recognition. International Conference on Document Analysis and Recognition, Sydney, 2019, pp. 1403-1409. DOI: 10.1109/ICDAR.2019.00226
17. Siddiqui S.A., Khan P.I., Dengel A., Ahmed S. Rethinking Semantic Segmentation for Table Structure Recognition in Documents. International Conference on Document Analysis and Recognition, Sydney, 2019, pp. 1397-1402. DOI: 10.1109/ICDAR.2019.00225
18. Tensmeyer C., Morariu V.I., Price B.L., Cohen S., Martinez T.R. Deep Splitting and Merging for Table Structure Decomposition. International Conference on Document Analysis and Recognition, Sydney, 2019, pp. 114-121. DOI: 10.1109/ICDAR.2019.00027
19. Palm R.B., Winther O., Laws F. CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks. International Conference on Document Analysis and Recognition, Kyoto, 2017, pp. 406-413. DOI: 10.1109/ICDAR.2017.74
20. Li Minghao, Cui Lei, Huang Shaohan, Wei Furu, Zhou Ming, Li Zhoujun. TableBank: A Benchmark Dataset for Table Detection and Recognition. Proceedings of the Twelfth Language Resources and Evaluation Conference, Marseille, 2020, pp. 1918-1925.
21. ICDAR 2013. Available at: https://paperswithcode.com/dataset/icdar-2013 (accessed on 08.10.2023)
22. Smart Document Engine - Automatic Analysis and Data Extraction from Business Documents for Desktop, Server and Mobile Platforms. Available at: https://smartengines.com/ocr-engines/document-scanner (accessed on 09.10.2023)