Abstract
This paper proposes a method to distinguish handwritten character regions from machine-printed ones using Hough transform (HT). The Gabor filtering in the human early vision realizes a type of Fourier transform (FT). Previously we proposed a FT-based distinction method successfully. However, we noticed simultaneously that the HT, instead of FT, may extract more features when we deal with characters which are regarded as piles of line segments. Experiments show that HT-based method, in combination with real-space features, achieves higher accuracy than the FT-based method. At the same time, the total calculation cost is found lower.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ding, X., Chen, L., Wu, T.: Character independent font recognition on a single chinese character. IEEE Trans. Pattern Anal., 195–204 (2007)
Kavallieratou, E., Stamatatos, S.: Discrimination of machine-printed from handwritten text using simple structural characteristics. In: International Conference on Pattern Recognition, pp. 437–440 (2004)
Wang, S.L., Fan, C.K., Tu, T.Y.: Classificationof machine-printed and handwritten texts using character block layout variance. Pattern Recognition, 1275–1284, 437–440 (1998)
Koyama, J., Kato, M., Hirose, A.: Distinction between handwritten and machine-printed characters without extracting characters or text lines. In: Proc. of World Congress on Computational Intelligence, International Joint Conference on Neural Networks (IJCNN), Hong Kong, pp. 4143–4150 (2008)
Koyama, J., Kato, M., Hirose, A.: Local-spectrum-based distinction between handwritten and machine-printed characters. In: Int’l Conf. on Image Processing, San Diego, pp. 12–15 (2008)
Hough, P.V.C.: U.S. Patent 3069654: method and means for recognizing complex patterns (1962)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Konno, Y., Hirose, A. (2012). Early-Vision-Inspired Method to Distinguish between Handwritten and Machine-Printed Character Images Using Hough Transform. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34500-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-34500-5_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34499-2
Online ISBN: 978-3-642-34500-5
eBook Packages: Computer ScienceComputer Science (R0)