TDEM: Table Data Extraction Model Based on Cell Segmentation

To accurately extract tabular data, we propose a novel cell-based tabular data extraction model (TDEM). The key of TDEM is to utilize grayscale projection of row separation lines, coupled with table masks and column masks generated by the VGG-19 neural network, to segment each individual cell from t...

Full description

Saved in:
Bibliographic Details
Published inIEICE Transactions on Information and Systems Vol. E107.D; no. 10; pp. 1376 - 1379
Main Authors WANG, Zhe, LU, Zhe-Ming, LUO, Hao, ZHENG, Yang-Ming
Format Journal Article
LanguageEnglish
Published The Institute of Electronics, Information and Communication Engineers 01.10.2024
Subjects
information extraction
table structure recognition
text recognition
Online AccessGet full text

Cover

More Information
Summary:To accurately extract tabular data, we propose a novel cell-based tabular data extraction model (TDEM). The key of TDEM is to utilize grayscale projection of row separation lines, coupled with table masks and column masks generated by the VGG-19 neural network, to segment each individual cell from the input image of the table. In this way, the text content of the table is extracted from a specific single cell, which greatly improves the accuracy of table recognition.
ISSN:0916-8532
1745-1361
DOI:10.1587/transinf.2024EDL8029