Arabic Printed Word Recognition Using Windowed Bernoulli HMMs

  • Ihab Khoury
  • Adrià Giménez
  • Alfons Juan
  • Jesús Andrés-Ferrer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


Hidden Markov Models (HMMs) are now widely used for off-line text recognition in many languages and, in particular, Arabic. In previous work, we proposed to directly use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea was to by-pass feature extraction and to ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. More recently, we extended the column bit vectors by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. However, these models might have limited capability to properly model vertical image distortions. In this paper, we have considered three methods of window repositioning after window extraction to overcome this limitation. Each sliding window is translated (repositioned) to align its center to the center of mass. Using this approach, state-of-art results are reported on the Arabic Printed Text Recognition (APTI) database.


Bernoulli HMMs APTI Arabic Printed Recognition Sliding Window Repositioning 


  1. 1.
    Dehghan, M., et al.: Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognition 34(5), 1057–1065 (2001), MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Giménez, A., Juan, A.: Embedded Bernoulli Mixture HMMs for Handwritten Word Recognition. In: ICDAR 2009, Barcelona, Spain, pp. 896–900 (July 2009)Google Scholar
  3. 3.
    Giménez, A., Khoury, I., Juan, A.: Windowed Bernoulli Mixture HMMs for Arabic Handwritten Word Recognition. In: ICFHR 2010, Kolkata, India, pp. 533–538 (November 2010)Google Scholar
  4. 4.
    Grosicki, E., El Abed, H.: ICDAR 2009 Handwriting Recognition Competition. In: ICDAR 2009, Barcelona, Spain, pp. 1398–1402 (July 2009)Google Scholar
  5. 5.
    Günter, S., et al.: HMM-based handwritten word recognition: on the optimization of the number of states, training iterations and Gaussian components. Pattern Recognition 37, 2069–2079 (2004)CrossRefGoogle Scholar
  6. 6.
    Märgner, V., El Abed, H.: ICDAR 2007 - Arabic Handwriting Recognition Competition. In: ICDAR 2007, Curitiba, Brazil, pp. 1274–1278 (September 2007)Google Scholar
  7. 7.
    Märgner, V., El Abed, H.: ICDAR 2009 Arabic Handwriting Recognition Competition. In: ICDAR 2009, Barcelona, Spain, pp. 1383–1387 (July 2009)Google Scholar
  8. 8.
    Pechwitz, M., et al.: IFN/ENIT - database of handwritten Arabic words. In: CIFED 2002, Hammamet, Tunis, pp. 21–23 (October 2002)Google Scholar
  9. 9.
    Rabiner, L., Juang, B.: Fundamentals of speech recognition. Prentice-Hall (1993)Google Scholar
  10. 10.
    Slimane, F., et al.: A new arabic printed text image database and evaluation protocols. In: ICDAR 2009, pp. 946–950 (July 2009)Google Scholar
  11. 11.
    Slimane, F., et al.: ICDAR 2011 - arabic recognition competition: Multi-font multi-size digitally represented text. In: ICDAR 2011 - Arabic Recognition Competition, pp. 1449–1453. IEEE (September 2011)Google Scholar
  12. 12.
    Young, S.: et al.: The HTK Book. Cambridge University Engineering Department (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ihab Khoury
    • 1
  • Adrià Giménez
    • 1
  • Alfons Juan
    • 1
  • Jesús Andrés-Ferrer
    • 1
  1. 1.DSIC/ITIUniversitat Politècnica de ValènciaValènciaSpain

Personalised recommendations