start-ver=1.4
cd-journal=joma
no-vol=15
cd-vols=
no-issue=12
article-no=
start-page=471
end-page=
dt-received=
dt-revised=
dt-accepted=
dt-pub-year=2022
dt-pub=20221211
dt-online=
en-article=
kn-article=
en-subject=
kn-subject=
en-title=
kn-title=A Proposal of Printed Table Digitization Algorithm with Image Processing
en-subtitle=
kn-subtitle=
en-abstract=
kn-abstract=Nowadays, digital transformation (DX) is the key concept to change and improve the operations in governments, companies, and schools. Therefore, any data should be digitized for processing by computers. Unfortunately, a lot of data and information are printed and handled on paper, although they may originally come from digital sources. Data on paper can be digitized using an optical character recognition (OCR) software. However, if the paper contains a table, it becomes difficult because of the separated characters by rows and columns there. It is necessary to solve the research question of "how to convert a printed table on paper into an Excel table while keeping the relationships between the cells?" In this paper, we propose a printed table digitization algorithm using image processing techniques and OCR software for it. First, the target paper is scanned into an image file. Second, each table is divided into a collection of cells where the topology information is obtained. Third, the characters in each cell are digitized by OCR software. Finally, the digitalized data are arranged in an Excel file using the topology information. We implement the algorithm on Python using OpenCV for the image processing library and Tesseract for the OCR software. For evaluations, we applied the proposal to 19 scanned and 17 screenshotted table images. The results show that for any image, the Excel file is generated with the correct structure, and some characters are misrecognized by OCR software. The improvement will be in future works.
en-copyright=
kn-copyright=

en-aut-name=ShiChenrui
en-aut-sei=Shi
en-aut-mei=Chenrui
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=1
ORCID=

en-aut-name=FunabikiNobuo
en-aut-sei=Funabiki
en-aut-mei=Nobuo
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=2
ORCID=

en-aut-name=HuoYuanzhi
en-aut-sei=Huo
en-aut-mei=Yuanzhi
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=3
ORCID=

en-aut-name=MentariMustika
en-aut-sei=Mentari
en-aut-mei=Mustika
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=4
ORCID=

en-aut-name=SugaKohei
en-aut-sei=Suga
en-aut-mei=Kohei
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=5
ORCID=

en-aut-name=ToshidaTakashi
en-aut-sei=Toshida
en-aut-mei=Takashi
kn-aut-name=
kn-aut-sei=
kn-aut-mei=
aut-affil-num=6
ORCID=

affil-num=1
en-affil=Department of Information and Communication Systems, Graduate School of Natural Science and Technology, Okayama University
kn-affil=

affil-num=2
en-affil=Department of Information and Communication Systems, Graduate School of Natural Science and Technology, Okayama University
kn-affil=

affil-num=3
en-affil=Department of Information and Communication Systems, Graduate School of Natural Science and Technology, Okayama University
kn-affil=

affil-num=4
en-affil=Department of Information Technology, State Polytechnic of Malang
kn-affil=

affil-num=5
en-affil=Astrolab
kn-affil=

affil-num=6
en-affil=Astrolab
kn-affil=
en-keyword=digitization
kn-keyword=digitization
en-keyword=printed table
kn-keyword=printed table
en-keyword=OCR
kn-keyword=OCR
en-keyword=Python
kn-keyword=Python
en-keyword=OpenCV
kn-keyword=OpenCV
en-keyword=Tesseract
kn-keyword=Tesseract
END