Abstract
This paper proposes a character segmentation system for Korean printed postal images. The proposed method is composed of two main processes, which are robust skew correction and character segmentation. Experimental results on real postal images show that the proposed system effectively segments characters to be suitable for the input of OCR system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kim, H.Y., Lim, K.T., Kim, D.S.: Postal Envelope Image Recognition System for Postal Automation. The KIPS Transactions Part B 10-B(4), 429–441 (2003)
Lee, J.S., Kwon, O.J., Bang, S.Y.: Highly Accurate Recognition of printed Korean Characters through an Improved Two-stage Classification Method. Pattern Recognition 32, 1935–1945 (1999)
Liang, S., Ahmadi, M., Shridhard, M.: Segmentation of Touching Characters in Printed Document Recognition. In: Second Int’l Conf. Document Analysis and Recognition, pp. 569–572 (1993)
Jang, S.I., Jeong, S.H., Nam, Y.S.: Classification of Machine-Printed and Handwritten Addresses on Korean Mail Piece Images Using Geometric Features. In: 17th International Conference on Pattern Recognition (ICPR 2004), pp. 383–386 (2004)
Haykin, S.: Neural Networks. Macmillan College Publishing Company, New Jersey (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jang, SK., Shin, JH., Oh, HH., Jang, SI., Chien, SI. (2005). Robust Character Segmentation System for Korean Printed Postal Images. In: Ali, M., Esposito, F. (eds) Innovations in Applied Artificial Intelligence. IEA/AIE 2005. Lecture Notes in Computer Science(), vol 3533. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11504894_13
Download citation
DOI: https://doi.org/10.1007/11504894_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26551-1
Online ISBN: 978-3-540-31893-4
eBook Packages: Computer ScienceComputer Science (R0)