Recognition of OCR Invoice Metadata Block Types

D 2018

Recognition of OCR Invoice Metadata Block Types

HA, Hien Thi, Aleš HORÁK, Marek MEDVEĎ and Zuzana NEVĚŘILOVÁ

Basic information

Original name

Recognition of OCR Invoice Metadata Block Types

Authors

HA, Hien Thi (704 Viet Nam, belonging to the institution), Aleš HORÁK (203 Czech Republic, guarantor, belonging to the institution), Marek MEDVEĎ (703 Slovakia, belonging to the institution) and Zuzana NEVĚŘILOVÁ (203 Czech Republic, belonging to the institution)

Edition

Switzerland, Text, Speech, and Dialogue, 21st International Conference, TSD 2018, p. 304-312, 9 pp. 2018

Publisher

Springer International Publishing

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/18:00103049

Organization unit

Faculty of Informatics

ISBN

978-3-030-00793-5

ISSN

DOI

http://dx.doi.org/10.1007/978-3-030-00794-2_33

UT WoS

000611532300033

Keywords in English

OCR;scanned documents;document metadata;invoice metadata extraction

Abstract

V originále

Automatically cataloging of thousands of paper-based structured documents is a crucial fund-saving task for future document management systems. Current optical character recognition (OCR) systems process the tabular data with a sufficient level of character-level accuracy; however, the overall structure of the document metadata is still an open practical task. In this paper, we introduce the OCRMiner system designed to extract the indexing metadata of structured documents obtained from an image scanning process and OCR. We present the details of the system modular architecture and evaluate the detection of text block types that appear within invoice documents. The system is based on text analysis in combination of layout features, and is developed and tested in cooperation with a renowned copy machine producer. The system uses an open source OCR and reaches the overall accuracy of 80.1%.

Links

MUNI/A/0854/2017, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.

Investor: Masaryk University, Category A

MUNI/33/55939/2017, interní kód MU

Name: Ověření úspěšnosti technik zpracování přirozeného jazyka pro extrakci informací ze skenovaných dokumentů

Investor: Masaryk University

Citovat

HA, Hien Thi, Aleš HORÁK, Marek MEDVEĎ and Zuzana NEVĚŘILOVÁ. Recognition of OCR Invoice Metadata Block Types. In P. Sojka, A. Horák, I. Kopeček, K. Pala. Text, Speech, and Dialogue, 21st International Conference, TSD 2018. Switzerland: Springer International Publishing, 2018, p. 304-312. ISBN 978-3-030-00793-5. Available from: https://dx.doi.org/10.1007/978-3-030-00794-2_33.

@inproceedings{1421338,
   author = {Ha, Hien Thi and Horák, Aleš and Medveď, Marek and Nevěřilová, Zuzana},
   address = {Switzerland},
   booktitle = {Text, Speech, and Dialogue, 21st International Conference, TSD 2018},
   doi = {http://dx.doi.org/10.1007/978-3-030-00794-2_33},
   editor = {P. Sojka, A. Horák, I. Kopeček, K. Pala},
   keywords = {OCR;scanned documents;document metadata;invoice metadata extraction},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-030-00793-5},
   pages = {304-312},
   publisher = {Springer International Publishing},
   title = {Recognition of OCR Invoice Metadata Block Types},
   year = {2018}
}

TY  - JOUR
ID  - 1421338
AU  - Ha, Hien Thi - Horák, Aleš - Medveď, Marek - Nevěřilová, Zuzana
PY  - 2018
TI  - Recognition of OCR Invoice Metadata Block Types
PB  - Springer International Publishing
CY  - Switzerland
SN  - 9783030007935
KW  - OCR;scanned documents;document metadata;invoice metadata extraction
N2  - Automatically cataloging of thousands of paper-based structured documents is a crucial fund-saving task for future document management systems. Current optical character recognition (OCR) systems process the tabular data with a sufficient level of character-level accuracy; however, the overall structure of the document metadata is still an open practical task. In this paper, we introduce the OCRMiner system designed to extract the indexing metadata of structured documents obtained from an image scanning process and OCR. We present the details of the system modular architecture and evaluate the detection of text block types that appear within invoice documents. The system is based on text analysis in combination of layout features, and is developed and tested in cooperation with a renowned copy machine producer. The system uses an open source OCR and reaches the overall accuracy of 80.1%.
ER  -

HA, Hien Thi, Aleš HORÁK, Marek MEDVEĎ and Zuzana NEVĚŘILOVÁ. Recognition of OCR Invoice Metadata Block Types. In P. Sojka, A. Horák, I. Kopeček, K. Pala. \textit{Text, Speech, and Dialogue, 21st International Conference, TSD 2018}. Switzerland: Springer International Publishing, 2018, p.~304-312. ISBN~978-3-030-00793-5. Available from: https://dx.doi.org/10.1007/978-3-030-00794-2\_{}33.

Detailed Information on Publication Record