The QCRI Recognition System for Handwritten Arabic

  • Felix StahlbergEmail author
  • Stephan Vogel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9280)


This paper describes our recognition system for handwritten Arabic. We propose novel text line image normalization procedures and a new feature extraction method. Our recognition system is based on the Kaldi recognition toolkit which is widely used in automatic speech recognition (ASR) research. We show that the combination of sophisticated text image normalization and state-of-the art techniques originating from ASR results in a very robust and accurate recognizer. Our system outperforms the best systems in the literature by over 20% relative on the abcde-s configuration of the IFN/ENIT database and achieves comparable performance on other configurations. On the KHATT corpus, we report 11% relative improvement compared to the best system in the literature.


Arabic Handwriting recognition Text image normalization 


  1. 1.
    Ahmad, I., Fink, G.A., Mahmoud, S.A.: Improvements in sub-character HMM model based arabic text recognition. In: ICFHR (2014)Google Scholar
  2. 2.
    Anastasakos, T., McDonough, J., Schwartz, R., Makhoul, J.: A compact model for speaker-adaptive training. In: ICSL. IEEE (1996)Google Scholar
  3. 3.
    Azeem, S.A., Ahmed, H.: Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models. IJDAR 16(4), 399–412 (2013)CrossRefGoogle Scholar
  4. 4.
    Dreuw, P., Rybach, D., Gollan, C., Ney, H.: Writer adaptive training and writing variant model refinement for offline arabic handwriting recognition. In: ICDAR. IEEE (2009)Google Scholar
  5. 5.
    Duda, R.O., Hart, P.E.: Use of the Hough transformation to detect lines and curves in pictures. Communications of the ACM 15(1) (1972)Google Scholar
  6. 6.
    El-Mahallawy, M.S.M.: A Large Scale HMM-Based Omni Font-Written OCR System for Cursive Scripts. Ph.D. thesis, Faculty of Engineering, Cairo University Giza, Egypt (2008)Google Scholar
  7. 7.
    Gales, M.: Semi-tied covariance matrices for hidden Markov models. Transactions on Speech and Audio Processing 7(3), 272–281 (1999)CrossRefGoogle Scholar
  8. 8.
    Hamdani, M., Mousa, A.D., Ney, H.: Open vocabulary arabic handwriting recognition using morphological decomposition. In: ICDAR. IEEE (2013)Google Scholar
  9. 9.
    Huang, X., Acero, A., Hon, H.W., R., R.: Spoken language processing: a guide to theory, algorithm, and system development. Prentice Hall PTR (2001)Google Scholar
  10. 10.
    Likforman-Sulem, L., Mohammad, R.A.H., Mokbel, C., Menasri, F., Bianne-Bernard, A., Kermorvant, C.: Features for HMM-based arabic handwritten word recognition systems. In: Guide to OCR for Arabic Scripts. Springer (2012)Google Scholar
  11. 11.
    Mahmoud, S.A., Ahmad, I., Alshayeb, M., Al-Khatib, W.G., Parvez, M.T., Fink, G.A., Märgner, V., Abed, H.E.: KHATT: arabic offline handwritten text database. In: ICFHR (2012)Google Scholar
  12. 12.
    Margner, V., Abed, H.E.: ICFHR 2010-arabic handwriting recognition competition. In: ICFHR. IEEE (2010)Google Scholar
  13. 13.
    Märgner, V., El Abed, H.: Arabic handwriting recognition competitions. In: Guide to OCR for Arabic Scripts, pp. 395–422. Springer (2012)Google Scholar
  14. 14.
    Pechwitz, M., Maddouri, S.S., Märgner, V., Ellouze, N., Amiri, H., et al.: IFN/ENIT-database of handwritten arabic words. In: CIFED (2002)Google Scholar
  15. 15.
    Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The kaldi speech recognition toolkit. In: ASRU (2011)Google Scholar
  16. 16.
    Povey, D., Zhang, X., Khudanpur, S.: Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging. CoRR (2014)Google Scholar
  17. 17.
    Rybach, D., Gollan, C., Heigold, G., Hoffmeister, B., Lööf, J., Schlüter, R., Ney, H.: The RWTH Aachen university open source speech recognition system. In: Interspeech (2009)Google Scholar
  18. 18.
    Stahlberg, F., Vogel, S.: Detecting dense foreground stripes in arabic handwriting for accurate baseline positioning. In: ICDAR. IEEE (2015) (to be published)Google Scholar
  19. 19.
    Young, S., Woodland, P., Evermann, G., Gales, M.: The HTK Toolkit 3.4. 1 (2013)Google Scholar
  20. 20.
    Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Communications of the ACM 27(3), 236–239 (1984)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Qatar Computing Research Institute, HBKUDohaQatar

Personalised recommendations