A Study on the Printed Uyghur Script Recognition Technique Using Word Visual Features

  • Halimulati MeimaitiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)


This paper proposes a recognition technique which applies a combination of image processing and pattern recognition to visual features of individual words. Uyghur script is naturally cursive, and its characters have uneven width. Therefore, in image format, precisely cutting Uyghur words into characters is difficult. To avoid such problem, we use word models instead of character models. Besides, this technique does not need a large amount of training samples: prepared text samples are converted to image samples which are used to construct individual word models.


Uyghur Visual features Recognition 


  1. 1.
    Ding, X., et al.: Character Recognition: Principles Methods and Practice. Tsinhua University Press (2017)Google Scholar
  2. 2.
    Wang, H., Ding, X.: Multi-font multi-typeface printing Uyghur character recognition. J. Tsinghua Univ. 44(7), 946–949 (2004)Google Scholar
  3. 3.
    Jin, J., Wang, H., Ding, X., Peng, L.: Printed Arabic document recognition system. In: DDR2005, pp. 48–55 (2005)Google Scholar
  4. 4.
    Arzigul, H.: Research and development of multi-font printing Uyghur character recognition system. Chin. J. Comput. 11,1480–1484 (2003)Google Scholar
  5. 5.
    Kadier, N., Peng, L.: A method of Uyghur and Arabic recognition based on HMM and statistical language model. Comput. Appl. Softw. 32(1), 171–174 (2015)Google Scholar
  6. 6.
    Naz, S., et al.: The optical character recognition of Urdu-like cursive scripts. Pattern Recognit. 47(3), 1229–1248 (2014)CrossRefGoogle Scholar
  7. 7.
    Al-Shatnawi, A.M., et al.: Skeleton extraction: comparison of five methods on the Arabic IFN/ENIT database. In: 2014 6th International Conference on Computer Science and Information Technology (CSIT), pp. 50–59 (2014)Google Scholar
  8. 8.
    Maqqor, A., et al.: Using HMM toolkit (HTK) for recognition of Arabic manuscripts characters. In: 2014 International Conference on Multimedia Computing and Systems (ICMCS) (2014)Google Scholar
  9. 9.
    Ahmad, I., Fink, G.A., Mahmoud, S.A.: Improvements in sub-character HMM model based Arabic text recognition. In: 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR) (2014)Google Scholar
  10. 10.
    Jiang, Z., Ding, X., Peng, L., Liu, C.: Modified bootstrap approach with state number optimization for hidden markov model estimation in small-size printed arabic text line recognition. In: Perner, P. (ed.) MLDM 2014. LNCS (LNAI), vol. 8556, pp. 437–441. Springer, Cham (2014). Scholar
  11. 11.
    Ait-Mohand, K., Paquet, T., Ragot, N.: Combining structure and parameter adaptation of HMMs for printed text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 36(9), 1716–1732 (2014)CrossRefGoogle Scholar
  12. 12.
    Moysset, B., et al.: The A2iA multi-lingual text recognition system at the second maurdor evaluation. In: 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR) (2014)Google Scholar
  13. 13.
    Mamat, H., Xiaojiao, C.: A method for printed Uyghur character segmentation. In: Liu, C.-L., Zhang, C., Wang, L. (eds.) CCPR 2012. CCIS, vol. 321, pp. 539–547. Springer, Heidelberg (2012). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of Information Science and EngineeringXinjiang UniversityUrumqiChina
  2. 2.Key Laboratory of Multilanguage Information TechnologyUrumqiChina

Personalised recommendations