Details
Originalsprache | Englisch |
---|---|
Titel des Sammelwerks | 2019 International Conference on Document Analysis and Recognition (ICDAR) |
Untertitel | Proceedings |
Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
Seiten | 1438-1443 |
Seitenumfang | 6 |
ISBN (elektronisch) | 978-1-7281-3014-9 |
ISBN (Print) | 978-1-7281-3015-6 |
Publikationsstatus | Veröffentlicht - Sept. 2019 |
Veranstaltung | 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australien Dauer: 20 Sept. 2019 → 25 Sept. 2019 |
Publikationsreihe
Name | Proceedings of the International Conference on Document Analysis and Recognition |
---|---|
ISSN (Print) | 1520-5363 |
ISSN (elektronisch) | 2379-2140 |
Abstract
In recent years, the problem of scene text extraction from images has received extensive attention and significant progress. However, text extraction from scholarly figures such as plots and charts remains an open problem, in part due to the difficulty of locating irregularly placed text lines. To the best of our knowledge, literature has not described the implementation of a text extraction system for scholarly figures that adapts deep convolutional neural networks used for scene text detection. In this paper, we propose a text extraction approach for scholarly figures that forgoes preprocessing in favor of using a deep convolutional neural network for text line localization. Our system uses a publicly available scene text detection approach whose network architecture is well suited to text extraction from scholarly figures. Training data are derived from charts in arXiv papers which are extracted using Allen Institute's pdffigures tool. Since this tool analyzes PDF data as a container format in order to extract text location through the mechanisms which render it, we were able to gather a large set of labeled training samples. We show significant improvement from methods in the literature, and discuss the structural changes of the text extraction pipeline.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2019 International Conference on Document Analysis and Recognition (ICDAR): Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. S. 1438-1443 8978202 (Proceedings of the International Conference on Document Analysis and Recognition).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - A neural approach for text extraction from scholarly figures
AU - Morris, David
AU - Tang, Peichen
AU - Ewerth, Ralph
N1 - Funding information: This work is financially supported by the German Federal Ministry of Education and Research (BMBF) and European Social Fund (ESF) (InclusiveOCW project, no. 01PE17004).
PY - 2019/9
Y1 - 2019/9
N2 - In recent years, the problem of scene text extraction from images has received extensive attention and significant progress. However, text extraction from scholarly figures such as plots and charts remains an open problem, in part due to the difficulty of locating irregularly placed text lines. To the best of our knowledge, literature has not described the implementation of a text extraction system for scholarly figures that adapts deep convolutional neural networks used for scene text detection. In this paper, we propose a text extraction approach for scholarly figures that forgoes preprocessing in favor of using a deep convolutional neural network for text line localization. Our system uses a publicly available scene text detection approach whose network architecture is well suited to text extraction from scholarly figures. Training data are derived from charts in arXiv papers which are extracted using Allen Institute's pdffigures tool. Since this tool analyzes PDF data as a container format in order to extract text location through the mechanisms which render it, we were able to gather a large set of labeled training samples. We show significant improvement from methods in the literature, and discuss the structural changes of the text extraction pipeline.
AB - In recent years, the problem of scene text extraction from images has received extensive attention and significant progress. However, text extraction from scholarly figures such as plots and charts remains an open problem, in part due to the difficulty of locating irregularly placed text lines. To the best of our knowledge, literature has not described the implementation of a text extraction system for scholarly figures that adapts deep convolutional neural networks used for scene text detection. In this paper, we propose a text extraction approach for scholarly figures that forgoes preprocessing in favor of using a deep convolutional neural network for text line localization. Our system uses a publicly available scene text detection approach whose network architecture is well suited to text extraction from scholarly figures. Training data are derived from charts in arXiv papers which are extracted using Allen Institute's pdffigures tool. Since this tool analyzes PDF data as a container format in order to extract text location through the mechanisms which render it, we were able to gather a large set of labeled training samples. We show significant improvement from methods in the literature, and discuss the structural changes of the text extraction pipeline.
KW - Document analysis
KW - Figure search
KW - Neural networks
KW - Text detection
KW - Text extraction
UR - http://www.scopus.com/inward/record.url?scp=85079880203&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2019.00231
DO - 10.1109/ICDAR.2019.00231
M3 - Conference contribution
AN - SCOPUS:85079880203
SN - 978-1-7281-3015-6
T3 - Proceedings of the International Conference on Document Analysis and Recognition
SP - 1438
EP - 1443
BT - 2019 International Conference on Document Analysis and Recognition (ICDAR)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Y2 - 20 September 2019 through 25 September 2019
ER -