Table Recognition and Recovery in the Camera-Captured Image with Complex Background

DOI

10.2991/asei-15.2015.27How to use a DOI?

Keywords

Form Recognition; OCR; Form Representation; Table Retrieval

Abstract

With the development of OCR techniques, people start to use image processing methods to analyze and process the image-type documents (typically scanned images) for obtaining the information of characters and the layout. On the other hand, table, draw relatively less attention in OCR even it is an important writing structure containing plenty of classified massages in special format. This paper comes up with an innovative method aiming to detect, recognize and recover the table on a camera-capture image with complicated background. This method mainly includes the preprocessing, binarization and edge detection of the image, together with the detection of cells, as well as the analysis and recovery of table structure. In practical experiments, Emgu CV is employed to achieve more accurate result with better efficiency.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Guiyang Xie
AU  - Yirong Mao
AU  - Zifan Nan
AU  - Shizhe Wang
AU  - Yue Li
AU  - Wei Wang
PY  - 2015/05
DA  - 2015/05
TI  - Table Recognition and Recovery in the Camera-Captured Image with Complex Background
BT  - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation
PB  - Atlantis Press
SP  - 121
EP  - 125
SN  - 2352-5401
UR  - https://doi.org/10.2991/asei-15.2015.27
DO  - 10.2991/asei-15.2015.27
ID  - Xie2015/05
ER  -