Abstract
This paper proposes a new approach to a method to estimate a skew angle of a rotated document image. This is realized by using Speeded-Up Robust Features (SURF), and the goal is that it enables the image to be rotated back to the correct orientation. SURF detects a number of keypoints both from the reference image on which a set of standard alphabets (e.g. letter eaf through ezf in a certain font) are written, and the image of the rotated document. Two nearest features each from the reference image and the input image are compared to decide to how many degrees the feature in the input image is rotated. Finally the skew angle of the whole input image( the global skew angle) is decided by the majority of the total votes of angles that have been calculated as mentioned above.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
O’Gorman, L., Kasturi, R.: Document Image Analysis. IEEE Computer Society, Los Alamitos (1997)
Liang, J., Doermann, D., Li, H.: Camera-based analysis of text and documents: a survey. International Journal on Document Analysis and Recognition 7, 84–104 (2005)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)
Uchida, S., et al.: Skew Estimation by Instances. In: The Eighth IAPR International Workshop on Document Analysis Systems, pp. 201–208 (2008)
Pal, U., Mitra, M., Chaudhuri, B.B.: Multi-skew detection of Indian script documents. In: Proc. Int. Conf. Doc. Anal. Recog., pp. 292–296 (2001)
Ishitani, Y.: Document skew detection based on local region complexity. In: Proc. Int. Conf. Doc. Anal. Recog., pp. 49–52 (1993)
Jiang, X., Bunke, H., Widmer-Kljajo, D.: Skew detection of document images by focused nearest-neighbor clustering. In: Proc. Int. Conf. Doc. Anal. Recog., pp. 629–632 (1999)
Lu, Y., Tan, C.L.: Improved nearest neighbor based approach to accurate document skew estimation. In: Proc. Int. Conf. Doc. Anal. Recog., pp. 503–507 (2003)
Lu, S., Tan, C.L.: Camera document restoration for OCR. In: Workshop Camera-Based Doc. Anal. Recog., pp. 17–24 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shiraishi, S., Feng, Y., Uchida, S. (2011). A New Approach for Instance-Based Skew Estimation. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based and Intelligent Information and Engineering Systems. KES 2011. Lecture Notes in Computer Science(), vol 6884. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23866-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-23866-6_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23865-9
Online ISBN: 978-3-642-23866-6
eBook Packages: Computer ScienceComputer Science (R0)