Information Extraction from Scanned Invoice Images using Text
Analysis and Layout Features

J 2022

Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features

HA, Hien Thi and Aleš HORÁK

Basic information

Original name

Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features

Authors

HA, Hien Thi (704 Viet Nam, belonging to the institution) and Aleš HORÁK (203 Czech Republic, belonging to the institution)

Edition

Signal Processing: Image Communication, Elsevier, 2022, 0923-5965

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Netherlands

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.500

RIV identification code

RIV/00216224:14330/22:00125095

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1016/j.image.2021.116601

UT WoS

000788052500011

Keywords in English

OCR; Information extraction; Scanned documents; Document metadata; Invoice metadata extraction; Metadata indexing

Abstract

V originále

While storing invoice content as metadata to avoid paper document processing may be the future trend, almost all of daily issued invoices are still printed on paper or generated in digital formats such as PDFs. In this paper, we introduce the OCRMiner system for information extraction from scanned document images which is based on text analysis techniques in combination with layout features to extract indexing metadata of (semi-)structured documents. The system is designed to process the document in a similar way a human reader uses, i.e. to employ different layout and text attributes in a coordinated decision. The system consists of a set of interconnected modules that start with (possibly erroneous) character-based output from a standard OCR system and allow to apply different techniques and to expand the extracted knowledge at each step. Using an open source OCR, the system is able to recover the invoice data in 90% for English and in 88% for the Czech set.

Links

LM2018101, research and development project

Name: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy (Acronym: LINDAT/CLARIAH-CZ)

Investor: Ministry of Education, Youth and Sports of the CR

MUNI/A/1195/2021, interní kód MU

Name: Aplikovaný výzkum v oblastech vyhledávání, analýz a vizualizací rozsáhlých dat, zpracování přirozeného jazyka a aplikované umělé inteligence

Investor: Masaryk University

Citovat

HA, Hien Thi and Aleš HORÁK. Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features. Signal Processing: Image Communication. Elsevier, 2022, vol. 102, No 1, p. 1-11. ISSN 0923-5965. Available from: https://dx.doi.org/10.1016/j.image.2021.116601.

@article{1810641,
   author = {Ha, Hien Thi and Horák, Aleš},
   article_number = {1},
   doi = {http://dx.doi.org/10.1016/j.image.2021.116601},
   keywords = {OCR; Information extraction; Scanned documents; Document metadata; Invoice metadata extraction; Metadata indexing},
   language = {eng},
   issn = {0923-5965},
   journal = {Signal Processing: Image Communication},
   title = {Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features},
   url = {https://www.sciencedirect.com/science/article/pii/S0923596521003015},
   volume = {102},
   year = {2022}
}

TY  - JOUR
ID  - 1810641
AU  - Ha, Hien Thi - Horák, Aleš
PY  - 2022
TI  - Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features
JF  - Signal Processing: Image Communication
VL  - 102
IS  - 1
SP  - 1-11
EP  - 1-11
PB  - Elsevier
SN  - 09235965
KW  - OCR
KW  - Information extraction
KW  - Scanned documents
KW  - Document metadata
KW  - Invoice metadata extraction
KW  - Metadata indexing
UR  - https://www.sciencedirect.com/science/article/pii/S0923596521003015
N2  - While storing invoice content as metadata to avoid paper document processing may be the future trend, almost all of daily issued invoices are still printed on paper or generated in digital formats such as PDFs. In this paper, we introduce the OCRMiner system for information extraction from scanned document images which is based on text analysis techniques in combination with layout features to extract indexing metadata of (semi-)structured documents. The system is designed to process the document in a similar way a human reader uses, i.e. to employ different layout and text attributes in a coordinated decision. The system consists of a set of interconnected modules that start with (possibly erroneous) character-based output from a standard OCR system and allow to apply different techniques and to expand the extracted knowledge at each step. Using an open source OCR, the system is able to recover the invoice data in 90% for English and in 88% for the Czech set.
ER  -

HA, Hien Thi and Aleš HORÁK. Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features. \textit{Signal Processing: Image Communication}. Elsevier, 2022, vol.~102, No~1, p.~1-11. ISSN~0923-5965. Available from: https://dx.doi.org/10.1016/j.image.2021.116601.

Detailed Information on Publication Record