Abstract
Currently, many businesses are using a manual approach for digitization of paper-based documents. This is a long and error-prone process and can be significantly sped up by automating the data extraction from the scanned documents. The automation will also significantly reduce the time and effort needed for the data extraction and can be a valuable opportunity for an organization to reduce costs. A solution is proposed which makes use of open-source components that can automate this process with minimal user input. The solution is also capable of handling common problems with images such as image skew and rotation caused by scanning the page at a slight angle or incorrect orientation respectively, along with watermark removal for improved extraction accuracy. It also handles full text pages along with forms or tabular data. The extraction of these can be performed with the help of a configuration file which contains keywords that help in identifying the fields in a form and map them into a structured format, which can be saved as XML and can be used for loading into a database system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Meng G et al (2010) Skew estimation of document images using bagging. IEEE Trans Image Process 19(7):1837–1846
Brodić D, Milivojevic ZN (2017) Text skew detection using combined entropy algorithm. Inform Technol Control 46(3):308–318
Lu S, Tan CL (2006) Automatic document orientation detection and categorization through document vectorization. In: Proceedings of the 14th ACM international conference on multimedia
Nikbakht P, Mahdavi M (2015) Targeted watermark removal of a SVD-based image watermarking scheme. In: 2015 7th conference on information and knowledge technology (IKT). IEEE, New York
Lai C-C (2011) An improved SVD-based watermarking scheme using human visual characteristics. Opt Commun 284(4):938–944
Langelaar GC, Lagendijk RL, Biemond J (1998) Removing spatial spread spectrum watermarks by non-linear filtering. In: 9th European signal processing conference (EUSIPCO 1998). IEEE, New York
Park J, Tai Y-W, Kweon IS (2012) Identigram/watermark removal using cross-channel correlation. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, New York
Kim J, Hwang H (2020) A rule-based method for table detection in website images. IEEE Access 8:81022–81033
Riba P et al (2019) Table detection in invoice documents by graph neural networks. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, New York
Paliwal SS et al (2019) TableNet: deep learning model for end-to-end table detection and tabular data extraction from scanned document images. In: 2019 international conference on document analysis and recognition (ICDAR). IEEE, New York
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kurhekar, P., Nigam, S., Pillai, S. (2021). Automated Text and Tabular Data Extraction from Scanned Document Images. In: Sharma, N., Chakrabarti, A., Balas, V.E., Bruckstein, A.M. (eds) Data Management, Analytics and Innovation. Lecture Notes on Data Engineering and Communications Technologies, vol 70. Springer, Singapore. https://doi.org/10.1007/978-981-16-2934-1_11
Download citation
DOI: https://doi.org/10.1007/978-981-16-2934-1_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2933-4
Online ISBN: 978-981-16-2934-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)