Abstract
Character segmentation is one of the most difficult stages in Uyghur recognition. In this paper, according to the writing style of the Uyghur, a method which is based on the image contour is proposed, it firstly calculates the baseline fields of the scanned image page by using Hough transformation, then segments the characters by adjusting the baseline fields, and finally merging the multiple parts by using the statistical part of the width. The Experimental results show a high correct segmentation rate and stability.
As Uyghur borrowing Arabic characters and part of the Persian characters, so the segmentation method also applies to the recognition of Arabic.
This is a preview of subscription content, log in via an institution to check access.
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
Jin, J.-m., Ding, X.-q., Peng, L.-r., Wang, H.: Printed Uyghur Texts Segmentation. Journal of Chinese Information Processing (Chinese) 18(5), 76–83 (2005)
Mutter, K.N., Jafri, M.Z.M., Aziz, A.A.: Real Time Object Detection Using Hopfield Neural Network for Arabic Printed Letter Recognition. In: 10th International Conference on Information Science, Signal Processing and their Applications (ISSPA 2010), pp. 770–773 (2010)
Zheng, L., Hassin., A.H., Tang, X.-l.: A New Algorithm for Machine Printed Arabic Character Segmentation. J. Pattern Recognition Letters 25, 1723–1729 (2004)
Zidouri, A., Sarfraz, M., Shahab, S.A.: Adaptive Dissection based Subword Segmentation of Printed Arabic Text.C. In: Proceedings of the Ninth International Conference on Information Visualisation, pp. 239–243 (2005)
Shirali-Shahreze, S., Manzuri-Shalmani, M.T., Hassan Shirali-Shahreze, M.: A Skew Resistant Method for Persian Text Segmentation. In: Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing (CIISP 2007), pp. 115–120 (2007)
Makridis, M., Nikolaou, N., Gatos, B.: An Efficient Word Segmentation Technique for Historical and Degraded Machine-printed Documents. C. In: Processdings of the Ninth International Conference on Document Analysis and Recognition, pp. 178–182 (2007)
Amin, A.: Segmentation of Printed Arabic Text. In: Singh, S., Murshed, N., Kropatsch, W.G. (eds.) ICAPR 2001. LNCS, vol. 2013, p. 115. Springer, Heidelberg (2001)
Hssini, M., Lazrek, A.: Graphical Segmentation of Arabic Word: Typographic point of view. In: Multimedia Computing and Systems (ICMCS), pp. 1–6 (2011)
Broumandnia, A., Shanbehzadeh, J., Nourani, M.: Segmentation of Printed Farsi/Arabic Words. In: IEEE/ACS International Conference on Computer Systems and Applications, pp. 761–766 (2007)
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
Mamat, H., Xiaojiao, C. (2012). A Method for Printed Uyghur Character Segmentation. In: Liu, CL., Zhang, C., Wang, L. (eds) Pattern Recognition. CCPR 2012. Communications in Computer and Information Science, vol 321. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33506-8_66
Download citation
DOI: https://doi.org/10.1007/978-3-642-33506-8_66
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33505-1
Online ISBN: 978-3-642-33506-8
eBook Packages: Computer ScienceComputer Science (R0)