Skip to main content
SpringerLink
Log in

The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images

  • Conference paper
  • First Online:
Document Analysis Systems (DAS 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12116))

Included in the following conference series:

Abstract

A correct localisation of tables in a document is instrumental for determining their structure and extracting their contents; therefore, table detection is a key step in table understanding. Nowadays, the most successful methods for table detection in document images employ deep learning algorithms; and, particularly, a technique known as fine-tuning. In this context, such a technique exports the knowledge acquired to detect objects in natural images to detect tables in document images. However, there is only a vague relation between natural and document images, and fine-tuning works better when there is a close relation between the source and target task. In this paper, we show that it is more beneficial to employ fine-tuning from a closer domain. To this aim, we train different object detection algorithms (namely, Mask R-CNN, RetinaNet, SSD and YOLO) using the TableBank dataset (a dataset of images of academic documents designed for table detection and recognition), and fine-tune them for several heterogeneous table detection datasets. Using this approach, we considerably improve the accuracy of the detection models fine-tuned from natural images (in mean a 17%, and, in the best case, up to a 60%).

This work was partially supported by Ministerio de Economía y Competitividad [MTM2017-88804-P], Ministerio de Ciencia, Innovación y Universidades [RTC-2017-6640-7], Agencia de Desarrollo Económico de La Rioja [2017-I-IDD-00018], and the computing facilities of Extremadura Research Centre for Advanced Technologies (CETA-CIEMAT), funded by the European Regional Development Fund (ERDF). CETA-CIEMAT belongs to CIEMAT and the Government of Spain.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Abdulla, W.: Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow (2017). https://github.com/matterport/Mask_RCNN

  2. Alexey, A.B.: YOLO darknet (2018). https://github.com/AlexeyAB/darknet

  3. Cesari, F., et al.: Trainable table location in document images. In: 16th International Conference on Pattern Recognition, ICPR 2002, vol. 3, p. 30236. ACM (2002)

    Google Scholar 

  4. Chen, T., et al.: MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. CoRR abs/1512.01274 (2015). http://arxiv.org/abs/1512.01274

  5. Colaboratory team: Google colaboratory (2017). https://colab.research.google.com

  6. Costa e Silva, A.: Learning rich hidden Markov models in document analysis: table location. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2010, pp. 843–847. IEEE (2009)

    Google Scholar 

  7. Coüasnon, B., Lemaitre, A.: Recognition of tables and forms. In: Doermann, D., Tombre, K. (eds.) Handbook of Document Image Processing and Recognition, pp. 647–677. Springer, London (2014). https://doi.org/10.1007/978-0-85729-859-1_20

    Chapter  Google Scholar 

  8. Embley, D.W., et al.: Table-processing paradigms: a research survey. Int. J. Doc. Anal. Recogn. 8(2–3), 647–677 (2006)

    Google Scholar 

  9. Everingham, M., et al.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98–136 (2015)

    Article  Google Scholar 

  10. Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: ICDAR2017 competition on page object detection. In: 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017, pp. 1417–1422 (2017)

    Google Scholar 

  11. Gilani, A., et al.: Table detection using deep learning. In: 14th International Conference on Document Analysis and Recognition, ICDAR 2017, pp. 771–776. IEEE (2017)

    Google Scholar 

  12. Girshick, R., et al.: Accurate object detection and semantic segmentation. In: 2014 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2014, pp. 580–587. IEEE (2014)

    Google Scholar 

  13. Gobel, M.C., Hassan, T., Oro, E., Orsi, G.: ICDAR2013 table competition. In: 12th ICDAR Robust Reading Competition, ICDAR 2013, pp. 1449–1453. IEEE (2013)

    Google Scholar 

  14. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org

  15. Hao, L., et al.: A table detection method for PDF documents based on convolutional neural networks. In: 12th International Workshop on Document Analysis Systems, DAS 2016, pp. 287–292. IEEE (2016)

    Google Scholar 

  16. Hirayama, Y.: A method for table structure analysis using DP matching. In: 3rd International Conference on Document Analysis and Recognition, ICDAR 1995, pp. 583–586. IEEE (1995)

    Google Scholar 

  17. Huang, Y., et al.: A YOLO-based table detection method. In: 15th International Conference on Document Analysis and Recognition, ICDAR 2019 (2019)

    Google Scholar 

  18. Institute of Computer Science and Technology of Peking University and Institute of Digital Publishing of Founder R&D Center, China: Marmot dataset for table recognition (2011). http://www.icst.pku.edu.cn/cpdp/sjzy/index.htm

  19. Jianying, H., et al.: Medium-independent table detection. In: Document Recognition and Retrieval VII. vol. 3967, pp. 583–586. International Society for Optics and Photonics (1999)

    Google Scholar 

  20. Kasar, T., et al.: Learning to detect tables in scanned document images using line information. In: 12th International Conference on Document Analysis and Recognition, ICDAR 2013, pp. 1185–1189. IEEE (2013)

    Google Scholar 

  21. Kerwat, M., George, R., Shujaee, K.: Detecting knowledge artifacts in scientific document images - comparing deep learning architectures. In: 5th International Conference on Social Networks Analysis, Management and Security, SNAMS 2018, pp. 147–152. IEEE (2018)

    Google Scholar 

  22. Kluyver, T., et al.: Jupyter notebooks – a publishing format for reproducible computational workflows. In: 20th International Conference on Electronic Publishing, pp. 87–90. IOS Press (2016)

    Google Scholar 

  23. Li, M., et al.: TableBank: Table Benchmark for Image-based Table Detection and Recognition. CoRR abs/1903.01949 (2019). http://arxiv.org/abs/1903.01949

  24. Lin, T., Goyal, P., Girshick, R., He, K., Dollár., P.: Keras retinanet (2017). https://github.com/fizyr/keras-retinanet

  25. Lin, T.Y., et al.: Focal loss for dense object detection. In: 16th International Conference on Computer Vision, ICCV 2017, pp. 2999–3007 (2017)

    Google Scholar 

  26. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  27. Oliveira, D.A.B., Viana, M.P.: Fast CNN-based document layout analysis. In: 14th International Conference on Computer Vision Workshops, ICCVW 2017, pp. 1173–1180. IEEE (2017)

    Google Scholar 

  28. Oro, E., Ruffolo, M.: PDF-TREX: an approach for recognizing and extracting tables from PDF documents. In: 10th International Conference on Document Analysis and Recognition, ICDAR 2009, pp. 906–910. IEEE (2009)

    Google Scholar 

  29. Razavian, A.S., et al.: CNN features off-the-shelf: an astounding baseline for recognition. In: 27th Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014, pp. 512–519 (2014)

    Google Scholar 

  30. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. CoRR abs/1804.02767 (2018). http://arxiv.org/abs/1804.02767

  31. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91–99 (2015)

    Google Scholar 

  32. Rosebrock, A.: Deep Learning for Computer Vision with Python. PyImageSearch (2018). https://www.pyimagesearch.com/

  33. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y

    Article  MathSciNet  Google Scholar 

  34. Schreiber, S., et al.: DeepDeSRT: deep learning for detection and structure recognition of tables in document images. In: 14th International Conference on Document Analysis and Recognition, ICDAR 2017, pp. 1162–1167. IEEE (2017)

    Google Scholar 

  35. Shahab, A., Shafait, F., Kieninger, T., Dengel, A.: An open approach towards the benchmarking of table structure recognition systems. In: 9th IAPR International Workshop on Document Analysis Systems, DAS 2010, pp. 113–120 (2010)

    Google Scholar 

  36. Siddiqui, S.A., et al.: DeCNT: deep deformable CNN for table detection. IEEE Access 6, 74151–74161 (2018)

    Article  Google Scholar 

  37. Suen, C.Y., et al.: ICDAR2019 Table Competition (2019). http://icdar2019.org/

  38. Zanibbi, R., Blostein, D., Cordy, J.R.: A survey of table recognition. Document Anal. Recogn. 7(1), 1–16 (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics and Computer Science, University of La Rioja, Logroño, Spain

    Ángela Casado-García, César Domínguez, Jónathan Heras, Eloy Mata & Vico Pascual

Authors
  1. Ángela Casado-García
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. César Domínguez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jónathan Heras
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Eloy Mata
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Vico Pascual
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ángela Casado-García .

Editor information

Editors and Affiliations

  1. Huazhong University of Science and Technology, Wuhan, China

    Xiang Bai

  2. Autonomous University of Barcelona, Barcelona, Spain

    Dimosthenis Karatzas

  3. Lehigh University, Bethlehem, PA, USA

    Daniel Lopresti

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Casado-García, Á., Domínguez, C., Heras, J., Mata, E., Pascual, V. (2020). The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images. In: Bai, X., Karatzas, D., Lopresti, D. (eds) Document Analysis Systems. DAS 2020. Lecture Notes in Computer Science(), vol 12116. Springer, Cham. https://doi.org/10.1007/978-3-030-57058-3_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-57058-3_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-57057-6

  • Online ISBN: 978-3-030-57058-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation