Abstract
We present an efficient method for character skew rectification in scene text images. The method is based on a novel skew estimators, which exploit intuitive glyph properties and which can be efficiently computed in a linear time. The estimators are evaluated on a synthetically generated data (including Latin, Cyrillic, Greek, Runic scripts) and real scene text images, where the skew rectification by the proposed method improves the accuracy of a state-of-the-art scene text recognition pipeline.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Neumann, L., Matas, J.: On combining multiple segmentations in scene text recognition. In: 2013 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 523–527. IEEE, California (2013)
Neumann, L., Matas, J.: Text localization in real-world images using efficiently pruned exhaustive search. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 687–691. IEEE Computer Society Conference Publishing Services (2011). (IEEE Computer Society Offices 2001 L Street N.W. Suite 700 Washington, DC 20036–4928, United States)
Baird, H.S.: Document Image Analysis. IEEE Computer Society Press, Los Alamitos (1995)
Papandreou, A., Gatos, B.: A novel skew detection technique based on vertical projections. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 384–388 (2011)
Epshtein, B.: Determining document skew using inter-line spaces. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 27–31 (2011)
Srihari, S., Govindaraju, V.: Analysis of textual images using the hough transform. Mach. Vis. Appl. 2, 141–153 (1989)
Bar-Yosef, I., Hagbi, N., Kedem, K., Dinstein, I.: Fast and accurate skew estimation based on distance transform. In: The Eighth IAPR International Workshop on Document Analysis Systems, DAS 2008, pp. 402–407 (2008)
Sun, C., Si, D.: Skew and slant correction for document images using gradient direction. In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, vol. 1, 142–146 (1997)
Ramer, U.: An iterative procedure for the polygonal approximation of plane curves. Comput. Graph. Image Process. 1, 244–256 (1972)
Toussaint, G.: Solving geometric problems with the rotating calipers (1983)
Sklansky, J.: Finding the convex hull of a simple polygon. Pattern Recogn. Lett. 1, 79–83 (1982)
Shahab, A., Shafait, F., Dengel, A.: Icdar 2011 robust reading competition challenge 2: Reading text in scene images. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 1491–1496 (2011)
Acknowledgment
The authors were supported by the EU project MASELTOV (FP7-ICT-288587) and by the Czech Science Foundation Project GACR P103/12/G084. Lukáš would also like to acknowledge the support of the Google PhD Fellowship in Computer Vision and the Google Research Award.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Bušta, M., Drtina, T., Helekal, D., Neumann, L., Matas, J. (2015). Efficient Character Skew Rectification in Scene Text Images. In: Jawahar, C., Shan, S. (eds) Computer Vision - ACCV 2014 Workshops. ACCV 2014. Lecture Notes in Computer Science(), vol 9009. Springer, Cham. https://doi.org/10.1007/978-3-319-16631-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-16631-5_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16630-8
Online ISBN: 978-3-319-16631-5
eBook Packages: Computer ScienceComputer Science (R0)