TY - GEN
T1 - A cell-detection-based table-structure recognition method
AU - Ohta, Manabu
AU - Yamada, Ryoya
AU - Kanazawa, Teruhito
AU - Takasu, Atsuhiro
N1 - Funding Information:
This work was supported by a JSPS Grant-in-Aid for Scientific Research (C) (18K11989), Cross-ministerial Strategic Innovation Promotion Program (SIP) Second Phase, ?Big-data and AI-enabled Cyberspace Technologies? by New Energy and Industrial Technology Development Organization (NEDO), and the Collaborative Research Program of the National Institute of Informatics.
Publisher Copyright:
© 2019 Association for Computing Machinery.
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
T2 - 19th ACM Symposium on Document Engineering, DocEng 2019
Y2 - 23 September 2019 through 26 September 2019
ER -