Abstract
Uyghur location for tilted text is of great significance for character recognition. Existing text region localization method is not effective for Uyghur text region. This paper proposed a new method to solve this problem. Firstly extracting rule feature of candidate regions, striking out the noise, then correcting the angle of the tilted text to detect the non-text area; Finally proposing polygon-location algorithm based on the special writing style of Uyghur, which can reduce the interference coming from the background in the process of recognition. The location accuracy is more than 91%.
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
Abudureyimu, H., Jume, E., Maitimusha, K., Hao, H.: Uighur Character Recognition Based on Adaptive Models. In: 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 476–479 (2012)
Kumar, M., Lee, G.: Automatic Text Location from Complex Natural Scene Images, 594–597. IEEE (2010)
Wang, Y., Tanaka, N.: Text String Extraction from Scene Image Based on Edge Feature and Morphology. In: The Eighth IAPR Workshop on Document Analysis Systems, pp. 323–328
Leon, M., Vilaplana, V., Gasull, A., et al.: Region-Based Caption Text Extraction. In: 2010 11th International Workshop on Image Analysis for Multimedia Interactive Services, pp. 1–4 (2010)
Lee, S., Cho, M.S., Jungz, K., et al.: Scene Text Extraction with Edge Constraint and Text Collinearity. In: 2010 International Conference on Pattern Recognition, pp. 3983–3986 (2010)
Li, N.-Y., Liang, Y.-M., Zhang, S., et al.: Text Location in Complex Color Images Based on BP Neural Network. Acta Photonica Sinica 38(10), 2713–2715 (2009)
Jung, J., Lee, S.H., Cho, M.S., Kim, J.H.: Scene Text Extractor Using Touchscreen Interface. ETRI Journal 33(1), 78–88 (2011)
Rengreng, D., Halidan, A.: An Adaptive-angle-method For Uyghur Location. In: 2012 Spring World Congress on Engineering and Technology, pp. 301–304 (2012)
Alves, W.A.L., Hashimoto, R.F.: Text Regions Extracted from Scene Images by Ultimate Attribute Opening and Decision Tree Classification. In: 2010 23rd SIBGRAPI - Conference on Graphics, Patterns and Images, pp. 360–367 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Abudureyimu, H., Deng, R., Maitimusha, K., Yang, N. (2013). Polygon-Location Method Based on Uyghur Text Regional Rules. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)