A cell-detection-based table-structure recognition method

Manabu Ohta, Ryoya Yamada, Teruhito Kanazawa, Atsuhiro Takasu

研究成果

9 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings of the ACM Symposium on Document Engineering, DocEng 2019
出版社Association for Computing Machinery, Inc
ISBN(電子版)9781450368872
DOI
出版ステータスPublished - 9月 23 2019
イベント19th ACM Symposium on Document Engineering, DocEng 2019 - Berlin
継続期間: 9月 23 20199月 26 2019

出版物シリーズ

名前Proceedings of the ACM Symposium on Document Engineering, DocEng 2019

Conference

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

ASJC Scopus subject areas

  • ソフトウェア
  • 情報システム

フィンガープリント

「A cell-detection-based table-structure recognition method」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル