Research on the Methods for Extracting the Sensitive Uyghur Text-Images for Digital Forensics

  • Yasen Aizezi
  • Anniwaer Jiamali
  • Ruxianguli Abdurixiti
  • Kurban UbulEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)


With the continuous development of filtration technology for text information, many criminal offenders made much harmful text information in Uyghur involving extreme religion and terrorism information by image editing software. In order to recognize the Uyghur text-images effectively, a scheme for recognizing printed Uyghur based on the features extracted by histogram of oriented gradient (HOG) and the multilayer perceptron (MLP) neural network is put forward. Firstly, preprocess the Uyghur text-images to obtain the binary images after eliminating noise. After that, segment the text-line by horizontal projection integral method and segment the words and characters by vertical projection integral method to obtain independent characters. Next, extract the features of characters by HOG. Finally, recognize the characters through the trained MLP neural network classifier and according to features extract by HOG. The experimental results showed that we could recognize Uyghur characters accurately by the method put forward.


Printed Uyghur Recognition Character segmentation Histogram of oriented gradient (HOG) Multilayer perceptron (MLP) 



This paper is supported by the National Natural Science Foundation of China (NSFC) (No. 61762086), the National Social Science Fund of China (No. 13CFX055) and the Science Research Program of the Higher Education Institute of Xinjiang (No. XJEDU2016I052, XJEDU2016S090, XJEDU2017M046).


  1. 1.
    Song, Y., Liu, Y., Wang, Y., Chen, Y.: A high performance text detection system based on SWT for RGB-D image. Microcomput. Appl. 31(9), 33–36 (2015)Google Scholar
  2. 2.
    Liu, W., Li, H.: Uighur character recognition based on multi-template normalization. J. Chin. Inf. Process. 30(1), 56–61 (2016)MathSciNetGoogle Scholar
  3. 3.
    Yu, B.: Research on Form and Chinese Characters Recognition in Printed Chinese Document Recognition System. Harbin Engineering University, 12 March 2011Google Scholar
  4. 4.
    Ubul, K., Adler, A., Abliz, G., et al.: Off-line Uyghur signature recognition based on modified grid information features. In: International Conference on Information Science, Signal Processing and Their Applications, pp. 1056–1061. IEEE (2012)Google Scholar
  5. 5.
    Chen, Q., Yuan, B., Li, X., Ren, H., Zhang, J.: Printed Uyghur characters recognition based on template matching. Comput. Technol. Dev. 22(4), 119–122 (2012)Google Scholar
  6. 6.
    Kadier, N., Peng, L., Halimulati: Uyghur and Arabic recognition methods based on HMM and statistical language model. Comput. Appl. Softw. 32(1), 171–174 (2015)Google Scholar
  7. 7.
    Jiang, Z., Ding, X., Peng, L.: Character model optimization for segmentation-free uyghur text line recognition. J. Tsinghua Univ. (Sci. Technol.) 55(8), 873–877 (2015)Google Scholar
  8. 8.
    Su, P., Mamat, H., Saypidin, A., Wang, J.: A Uyghur words feature extraction method based on the conjoined section. J. Xinjiang Univ. (Nat. Sci. Edn.) 32(4), 462–468 (2015)Google Scholar
  9. 9.
    Simayi, W., Ibrayim, M., Tursun, D., et al.: Research on on-line Uyghur character recognition technology based on center distance feature. In: IEEE International Symposium on Signal Processing and Information Technology, pp. 293–298. IEEE (2013)Google Scholar
  10. 10.
    Wan, J.: The Research and Implementation of the Key Technology in the printed Uyghur character recognition System. Xinjiang University, pp. 20–21 (2013)Google Scholar
  11. 11.
    Li, X., Yuan, B., Chen, Q., Ren, H., Zhang, J.: A segmentation method of printed Uyghur character based on projection histogram of pixels. Comput. Technol. Dev. 22(4), 41–49 (2012)Google Scholar
  12. 12.
    Liu, J., Bai, X.: Fuzzy Chinese character recognition of license based on Histogram of oriented gradients and Gaussian pyramid. J. Comput. Appl. 36(2), 586–590 (2016)Google Scholar
  13. 13.
    Kong, L., Tang, Y.: A Method for 3D Occlusion Face recognition based on wavelet transform and wavelet Neural network. Nat. Sci. Xiangtan Univ. 37(4), 82–86 (2015)Google Scholar
  14. 14.
    Mao, Y., Gui, X., Li, Q., He, X.: Study on application technology of deep learning. Appl. Res. Comput. 33(11), 3201–3205 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Yasen Aizezi
    • 1
  • Anniwaer Jiamali
    • 1
  • Ruxianguli Abdurixiti
    • 1
  • Kurban Ubul
    • 2
    Email author
  1. 1.Department of Information Security EngineeringXinjiang Police CollegeÜrümqiChina
  2. 2.School of Information Science and EngineeringXinjiang UniversityÜrümqiChina

Personalised recommendations