Abstract
Every day, thousands of digital documents are generated with useful information for companies, public organizations, and citizens. Given the impossibility of processing them manually, the automatic processing of these documents is becoming increasingly necessary in certain sectors. However, this task remains challenging, since in most cases a text-only based parsing is not enough to fully understand the information presented through different components of varying significance. In this regard, Document Layout Analysis (DLA) has been an interesting research field for many years, which aims to detect and classify the basic components of a document. In this work, we used a procedure to semi-automatically annotate digital documents with different layout labels, including 4 basic layout blocks and 4 text categories. We apply this procedure to collect a novel database for DLA in the public affairs domain, using a set of 24 data sources from the Spanish Administration. The database comprises 37.9K documents with more than 441.3K document pages, and more than 8M labels associated to 8 layout block units. The results of our experiments validate the proposed text labeling procedure with accuracy up to \(99\%\).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Antonacopoulos, A., et al.: A realistic dataset for performance evaluation of document layout analysis. In: ICDAR, pp. 296–300 (2009)
Bast, H., Korzen, C.: A benchmark and evaluation for text extraction from PDF. In: 2017 ACM/IEEE Joint Conference on Digital Libraries (2017)
Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877–1901 (2020)
Bukhari, S., et al.: Improved document image segmentation algorithm using multiresolution morphology. In: Document Recognition and Retrieval XVIII, vol. 7874, pp. 109–116 (2011)
Clausner, C., et al.: The ENP image and ground truth dataset of historical newspapers. In: ICDAR, pp. 931–935 (2015)
Clausner, C., et al.: ICDAR2017 competition on recognition of documents with complex layouts-RDCL2017. In: ICDAR, vol. 1, pp. 1404–1410 (2017)
DeAlcala, D., Serna, I., Morales, A., Fierrez, J., et al.: Measuring bias in AI models: an statistical approach introducing N-Sigma. In: COMPSAC (2023)
Eskenazi, S., et al.: A comprehensive survey of mostly textual document segmentation algorithms since 2008. Pattern Recogn. 64, 1–14 (2017)
Göbel, M., et al.: ICDAR 2013 table competition. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1449–1453 (2013)
He, K., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2961–2969 (2017)
Document management - Portable document format - Part 1: PDF 1.7. Standard, International Organization for Standardization (ISO) (2008)
Kenton, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Lang, T., et al.: Physical layout analysis of partly annotated newspaper images. In: Proceedings of the 23rd Computer Vision Winter Workshop, pp. 63–70 (2018)
Oliveira, D., Viana, M.: Fast CNN-based document layout analysis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1173–1180 (2017)
Peña, A., Morales, A., Fierrez, J., et al.: Leveraging large language models for topic classification in the domain of public affairs. In: ICDAR (2023)
Peña, A., Serna, I., et al.: Human-centric multimodal machine learning: recent advances and testbed on AI-based recruitment. SN Comput. Sci. 4, 434 (2023)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Sah, A., et al.: Text and non-text recognition using modified HOG descriptor. In: Proceedings of the IEEE Calcutta Conference, pp. 64–68 (2017)
Serna, I., et al.: Sensitive loss: improving accuracy and fairness of face representations with discrimination-aware deep learning. Artif. Intell. 305, 103682 (2022)
Soto, C., Yoo, S.: Visual detection with context for document layout analysis. In: EMNLP-IJCNLP, pp. 3464–3470 (2019)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wong, K., et al.: Document analysis system. IBM J. Res. Dev. 26(6), 647–656 (1982)
Zhong, X., et al.: PubLayNet: largest dataset ever for document layout analysis. In: ICDAR, pp. 1015–1022 (2019)
Acknowledgments
Support by VINCES Consulting under the project VINCESAI-ARGOS and BBforTAI (PID2021-127641OB-I00 MICINN/FEDER). The work of A. Peña is supported by a FPU Fellowship (FPU21/00535) by the Spanish MIU.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Annex
Annex
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Peña, A. et al. (2023). Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs. In: Coustaty, M., Fornés, A. (eds) Document Analysis and Recognition – ICDAR 2023 Workshops. ICDAR 2023. Lecture Notes in Computer Science, vol 14194. Springer, Cham. https://doi.org/10.1007/978-3-031-41501-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-41501-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41500-5
Online ISBN: 978-3-031-41501-2
eBook Packages: Computer ScienceComputer Science (R0)