Aligning document layouts extracted with different OCR engines with clustering approach
Layout analysis is essential step in information extraction from scanned document images. In this paper we propose an algorithm for aligning layouts generated with different OCR engines. The main requirement is to always generate the same layout for the given document image regardless of OCR engine...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-09-01
|
Series: | Egyptian Informatics Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1110866520301638 |
id |
doaj-144193e2d0cf457293b78a8dadd96312 |
---|---|
record_format |
Article |
spelling |
doaj-144193e2d0cf457293b78a8dadd963122021-09-19T04:55:13ZengElsevierEgyptian Informatics Journal1110-86652021-09-01223329338Aligning document layouts extracted with different OCR engines with clustering approachS. Tomovic0K. Pavlovic1M. Bajceta2Faculty of Mathematics and Natural Sciences, University of Montenegro, Cetinjska bb, 81000 Podgorica, Montenegro; Corresponding author.Faculty of Mathematics and Natural Sciences, University of Montenegro, Cetinjska bb, 81000 Podgorica, MontenegroDatum Solutions, 81000 Podogrica, MontenegroLayout analysis is essential step in information extraction from scanned document images. In this paper we propose an algorithm for aligning layouts generated with different OCR engines. The main requirement is to always generate the same layout for the given document image regardless of OCR engine used for image processing. In that way information extraction from scanned documents, that is heavily dependent on fields positions in the document, does not depend on specific OCR engine. In other words, it is sufficient to maintain universal extractor knowledge and not necessary to train extractor explicitly with samples processed on specific OCR engine. The proposed algorithm can handle administrative documents with complex layout.http://www.sciencedirect.com/science/article/pii/S1110866520301638Document layoutDocument indexingInformation retrievalClusteringOCR |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
S. Tomovic K. Pavlovic M. Bajceta |
spellingShingle |
S. Tomovic K. Pavlovic M. Bajceta Aligning document layouts extracted with different OCR engines with clustering approach Egyptian Informatics Journal Document layout Document indexing Information retrieval Clustering OCR |
author_facet |
S. Tomovic K. Pavlovic M. Bajceta |
author_sort |
S. Tomovic |
title |
Aligning document layouts extracted with different OCR engines with clustering approach |
title_short |
Aligning document layouts extracted with different OCR engines with clustering approach |
title_full |
Aligning document layouts extracted with different OCR engines with clustering approach |
title_fullStr |
Aligning document layouts extracted with different OCR engines with clustering approach |
title_full_unstemmed |
Aligning document layouts extracted with different OCR engines with clustering approach |
title_sort |
aligning document layouts extracted with different ocr engines with clustering approach |
publisher |
Elsevier |
series |
Egyptian Informatics Journal |
issn |
1110-8665 |
publishDate |
2021-09-01 |
description |
Layout analysis is essential step in information extraction from scanned document images. In this paper we propose an algorithm for aligning layouts generated with different OCR engines. The main requirement is to always generate the same layout for the given document image regardless of OCR engine used for image processing. In that way information extraction from scanned documents, that is heavily dependent on fields positions in the document, does not depend on specific OCR engine. In other words, it is sufficient to maintain universal extractor knowledge and not necessary to train extractor explicitly with samples processed on specific OCR engine. The proposed algorithm can handle administrative documents with complex layout. |
topic |
Document layout Document indexing Information retrieval Clustering OCR |
url |
http://www.sciencedirect.com/science/article/pii/S1110866520301638 |
work_keys_str_mv |
AT stomovic aligningdocumentlayoutsextractedwithdifferentocrengineswithclusteringapproach AT kpavlovic aligningdocumentlayoutsextractedwithdifferentocrengineswithclusteringapproach AT mbajceta aligningdocumentlayoutsextractedwithdifferentocrengineswithclusteringapproach |
_version_ |
1717376358897680384 |