Joint Handwritten Text Recognition and Word Classification for Tabular Information Extraction
(2022) 26TH International Conference on Pattern Recognition, 2022 p.1564-1570- Abstract
- In this paper, we present a system for extracting tabular information from loosely structured handwritten documents. The system consists of three parts, (i) a u-net like CNN-based method for text detection and segmentation, (ii) a new attention-based method for simultaneous text recognition and classification of word-parts, and (iii) a method for matching the word parts into a tabular structure for each entry. A key contribution is the observation that the new attention-based recognition and classification module makes it possible for improved spatial analysis of the tabular information. The method is evaluated on a unique historical document: The Swedish Wealth Tax of 1571, consisting of 11,453 pages of hand-written tax records. The... (More)
- In this paper, we present a system for extracting tabular information from loosely structured handwritten documents. The system consists of three parts, (i) a u-net like CNN-based method for text detection and segmentation, (ii) a new attention-based method for simultaneous text recognition and classification of word-parts, and (iii) a method for matching the word parts into a tabular structure for each entry. A key contribution is the observation that the new attention-based recognition and classification module makes it possible for improved spatial analysis of the tabular information. The method is evaluated on a unique historical document: The Swedish Wealth Tax of 1571, consisting of 11,453 pages of hand-written tax records. The evaluation shows that the system provides a significant improvement to the state-of-the-art to the problem of tabular extraction from loosely structured historical documents. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/b5f50e29-597f-474b-b687-ab45f476d11d
- author
- Blomqvist, Christopher
; Enflo, Kerstin
LU
; Jakobsson, Andreas LU
and Åström, Kalle LU
- organization
-
- Department of Economic History
- Growth, technological change, and inequality
- LTH Profile Area: AI and Digitalization
- eSSENCE: The e-Science Collaboration
- Mathematical Statistics
- Biomedical Modelling and Computation (research group)
- Statistical Signal Processing Group (research group)
- Stroke Imaging Research group (research group)
- Mathematics (Faculty of Engineering)
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- Mathematical Imaging Group (research group)
- publishing date
- 2022-11-29
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Histograms, Image segmentation, Text recognition, Finance, Writing, Information retrieval, Decoding
- host publication
- 2022 26th International Conference on Pattern Recognition (ICPR)
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 26TH International Conference on Pattern Recognition, 2022
- conference location
- Montreal, Canada
- conference dates
- 2022-08-21 - 2022-08-25
- external identifiers
-
- scopus:85128381076
- ISBN
- 978-1-6654-9063-4
- 978-1-6654-9062-7
- DOI
- 10.1109/ICPR56361.2022.9956282
- project
- Praise the people or praise the place: How culture and specialization drive long-term regional growth
- language
- English
- LU publication?
- yes
- id
- b5f50e29-597f-474b-b687-ab45f476d11d
- date added to LUP
- 2022-12-12 14:43:41
- date last changed
- 2024-06-13 21:41:09
@inproceedings{b5f50e29-597f-474b-b687-ab45f476d11d, abstract = {{In this paper, we present a system for extracting tabular information from loosely structured handwritten documents. The system consists of three parts, (i) a u-net like CNN-based method for text detection and segmentation, (ii) a new attention-based method for simultaneous text recognition and classification of word-parts, and (iii) a method for matching the word parts into a tabular structure for each entry. A key contribution is the observation that the new attention-based recognition and classification module makes it possible for improved spatial analysis of the tabular information. The method is evaluated on a unique historical document: The Swedish Wealth Tax of 1571, consisting of 11,453 pages of hand-written tax records. The evaluation shows that the system provides a significant improvement to the state-of-the-art to the problem of tabular extraction from loosely structured historical documents.}}, author = {{Blomqvist, Christopher and Enflo, Kerstin and Jakobsson, Andreas and Åström, Kalle}}, booktitle = {{2022 26th International Conference on Pattern Recognition (ICPR)}}, isbn = {{978-1-6654-9063-4}}, keywords = {{Histograms; Image segmentation; Text recognition; Finance; Writing; Information retrieval; Decoding}}, language = {{eng}}, month = {{11}}, pages = {{1564--1570}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Joint Handwritten Text Recognition and Word Classification for Tabular Information Extraction}}, url = {{http://dx.doi.org/10.1109/ICPR56361.2022.9956282}}, doi = {{10.1109/ICPR56361.2022.9956282}}, year = {{2022}}, }