A cell-detection-based table-structure recognition method

Manabu Ohta, Ryoya Yamada, Teruhito Kanazawa, Atsuhiro Takasu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

If tables are automatically recognized to extract the numerical values in them, digital documents containing such tables can be augmented with graphs generated using the recognized tables. In this paper, we propose a cell-detection-based table-structure recognition method for such automatic graph generation from tables. In detecting cells in a table, ruled lines are crucial but do not necessarily surround all cells. We therefore propose a method to detect cells by estimating implicit ruled lines, where necessary, to recognize the table structure. We demonstrate the effectiveness of the proposed method by experiments using the ICDAR 2013 table competition dataset.

Original languageEnglish
Title of host publicationProceedings of the ACM Symposium on Document Engineering, DocEng 2019
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450368872
DOIs
Publication statusPublished - Sep 23 2019
Event19th ACM Symposium on Document Engineering, DocEng 2019 - Berlin, Germany
Duration: Sep 23 2019Sep 26 2019

Publication series

NameProceedings of the ACM Symposium on Document Engineering, DocEng 2019

Conference

Conference19th ACM Symposium on Document Engineering, DocEng 2019
CountryGermany
CityBerlin
Period9/23/199/26/19

Fingerprint

Experiments

Keywords

  • PDF
  • Table-structure analysis
  • Table-structure recognition
  • XML

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Ohta, M., Yamada, R., Kanazawa, T., & Takasu, A. (2019). A cell-detection-based table-structure recognition method. In Proceedings of the ACM Symposium on Document Engineering, DocEng 2019 [3345412] (Proceedings of the ACM Symposium on Document Engineering, DocEng 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3342558.3345412

A cell-detection-based table-structure recognition method. / Ohta, Manabu; Yamada, Ryoya; Kanazawa, Teruhito; Takasu, Atsuhiro.

Proceedings of the ACM Symposium on Document Engineering, DocEng 2019. Association for Computing Machinery, Inc, 2019. 3345412 (Proceedings of the ACM Symposium on Document Engineering, DocEng 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ohta, M, Yamada, R, Kanazawa, T & Takasu, A 2019, A cell-detection-based table-structure recognition method. in Proceedings of the ACM Symposium on Document Engineering, DocEng 2019., 3345412, Proceedings of the ACM Symposium on Document Engineering, DocEng 2019, Association for Computing Machinery, Inc, 19th ACM Symposium on Document Engineering, DocEng 2019, Berlin, Germany, 9/23/19. https://doi.org/10.1145/3342558.3345412
Ohta M, Yamada R, Kanazawa T, Takasu A. A cell-detection-based table-structure recognition method. In Proceedings of the ACM Symposium on Document Engineering, DocEng 2019. Association for Computing Machinery, Inc. 2019. 3345412. (Proceedings of the ACM Symposium on Document Engineering, DocEng 2019). https://doi.org/10.1145/3342558.3345412
Ohta, Manabu ; Yamada, Ryoya ; Kanazawa, Teruhito ; Takasu, Atsuhiro. / A cell-detection-based table-structure recognition method. Proceedings of the ACM Symposium on Document Engineering, DocEng 2019. Association for Computing Machinery, Inc, 2019. (Proceedings of the ACM Symposium on Document Engineering, DocEng 2019).
@inproceedings{5bad8e9bd98b4aa49637280801f450e3,
title = "A cell-detection-based table-structure recognition method",
abstract = "If tables are automatically recognized to extract the numerical values in them, digital documents containing such tables can be augmented with graphs generated using the recognized tables. In this paper, we propose a cell-detection-based table-structure recognition method for such automatic graph generation from tables. In detecting cells in a table, ruled lines are crucial but do not necessarily surround all cells. We therefore propose a method to detect cells by estimating implicit ruled lines, where necessary, to recognize the table structure. We demonstrate the effectiveness of the proposed method by experiments using the ICDAR 2013 table competition dataset.",
keywords = "PDF, Table-structure analysis, Table-structure recognition, XML",
author = "Manabu Ohta and Ryoya Yamada and Teruhito Kanazawa and Atsuhiro Takasu",
year = "2019",
month = "9",
day = "23",
doi = "10.1145/3342558.3345412",
language = "English",
series = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2019",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2019",

}

TY - GEN

T1 - A cell-detection-based table-structure recognition method

AU - Ohta, Manabu

AU - Yamada, Ryoya

AU - Kanazawa, Teruhito

AU - Takasu, Atsuhiro

PY - 2019/9/23

Y1 - 2019/9/23

N2 - If tables are automatically recognized to extract the numerical values in them, digital documents containing such tables can be augmented with graphs generated using the recognized tables. In this paper, we propose a cell-detection-based table-structure recognition method for such automatic graph generation from tables. In detecting cells in a table, ruled lines are crucial but do not necessarily surround all cells. We therefore propose a method to detect cells by estimating implicit ruled lines, where necessary, to recognize the table structure. We demonstrate the effectiveness of the proposed method by experiments using the ICDAR 2013 table competition dataset.

AB - If tables are automatically recognized to extract the numerical values in them, digital documents containing such tables can be augmented with graphs generated using the recognized tables. In this paper, we propose a cell-detection-based table-structure recognition method for such automatic graph generation from tables. In detecting cells in a table, ruled lines are crucial but do not necessarily surround all cells. We therefore propose a method to detect cells by estimating implicit ruled lines, where necessary, to recognize the table structure. We demonstrate the effectiveness of the proposed method by experiments using the ICDAR 2013 table competition dataset.

KW - PDF

KW - Table-structure analysis

KW - Table-structure recognition

KW - XML

UR - http://www.scopus.com/inward/record.url?scp=85073365402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073365402&partnerID=8YFLogxK

U2 - 10.1145/3342558.3345412

DO - 10.1145/3342558.3345412

M3 - Conference contribution

AN - SCOPUS:85073365402

T3 - Proceedings of the ACM Symposium on Document Engineering, DocEng 2019

BT - Proceedings of the ACM Symposium on Document Engineering, DocEng 2019

PB - Association for Computing Machinery, Inc

ER -