Proceedings of the 2015 International Conference on Industrial Technology and Management Science

A Correction Algorithm for Document Images Based on Edge Contour

Authors
Jianhao Ding, Zhijie Lin, Lingyun Yu
Corresponding Author
Jianhao Ding
Available Online November 2015.
DOI
10.2991/itms-15.2015.27How to use a DOI?
Keywords
Algorithm;Document Image; Edge Contour
Abstract

For digitized document images with black border, this paper presents a simple and rapid correcting method. Firstly, we extract the contours using canny operator and find the inner contour with maximum area. The bounding box of the contour is used to calculate the inclined angle as the skew angle of the document image. According to the skew angle, we rotate the image around the bounding box center to correct it. Lastly we use the average color of the image to fill the skew corners due to correction and crop the black border outside the bounding box. The experiment results indicate that the presented algorithm is exact, efficient, also with robustness.

Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2015 International Conference on Industrial Technology and Management Science
Series
Advances in Computer Science Research
Publication Date
November 2015
ISBN
978-94-6252-123-0
ISSN
2352-538X
DOI
10.2991/itms-15.2015.27How to use a DOI?
Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Jianhao Ding
AU  - Zhijie Lin
AU  - Lingyun Yu
PY  - 2015/11
DA  - 2015/11
TI  - A Correction Algorithm for Document Images Based on Edge Contour
BT  - Proceedings of the 2015 International Conference on Industrial Technology and Management Science
PB  - Atlantis Press
SP  - 105
EP  - 108
SN  - 2352-538X
UR  - https://doi.org/10.2991/itms-15.2015.27
DO  - 10.2991/itms-15.2015.27
ID  - Ding2015/11
ER  -