Abstract
Recognizing unconstrained cursive Arabic handwritten text is a very challenging task the use of hybrid classification to take advantage of the strong modeling of Hidden Markov Models (HMM) and the large capacity of discrimination related to Multilayer Perceptron (MLP) is a very important component in recognition systems. The proposed work reports an effective method on improvement our previous work that takes into consideration the context of character by applying an embedded training based HMMs this HMM is enhanced by an Artificial neural network that are incorporated into the process of classification to estimate the emission probabilities. The experiments are done on the same benchmark IFN/ENIT database of our previous work to compare the results and show the effectiveness of hybrid classifier for enhancing the recognition rate the results are promising and encouraging.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alkhateeb, J.H., Pauplin, O., Ren, J., Jiang, J.: Performance of hidden Markov model and dynamic Bayesian network classifiers on handwritten Arabic word recognition. In: Knowledge-Based Systems, vol. 24, pp. 680–688 (2011)
Espanã-Boquera, S., Castro-Bleda, M.J., Gorbe-Moya, J., Zamora-Martinez, F.: Improving offline handwritten text recognition with hybrid HMM/ANN models (2011)
Plots, T., Fink, G.A.: Markov models for offline handwriting recognition: a survey. Int. J. Anal. Recongit. 12(4), 269–298 (2009)
Ahmad, I., Fink, G.A., Mahmoud, S.A.: Improvement in sub-character HMM model based Arabic text recognition. In: Proceedings of the 14th International Conference on Frontiers in Handwrting Recognition (2014)
Azeem, S., Ahmed, H.: Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models. Int. J. Doc. Anal. Recognit. 16(4), 399–412 (2013)
AlKhateeb, J.H., Ren, J., Jiang, J., Al-Muhtaseb, H.: Offline handwritten arabic cursive text recognition using hidden Markov models and re-ranking. Pattern Recogn. Lett. 32(8), 1081–1088 (2011)
Kessentini, Y., Paquet, T., Ben, A.: Hamadou off-line handwritten word recognition using multistream hidden Markov models. Pattern Recogn. Lett. 31, 60–70 (2010)
Maqqor, A., Halli, A., Satori, K., Tairi, H.: Off-line recognition handwriting combination of multiple classifiers. In: Proceedings of the 3rd International IEEE Colloquium on Information Science and Technology IEEE, CIST 2014, October 2014
El Moubtahij, H., Halli, A., Khalid, S.: Using features of local densities statistics and HMM toolkit (HTK) for offline Arabic handwriting text recognition (2016)
Jayech, K., Mahjoub, M.A., Ben Amara, N.: Arabic handwritten word recognition based on dynamic Bayesian network (2016)
van der Zwaag, B.-J.: Handwritten Digit Recognition: A Neural Network Demo (2016)
Chen, X.: Convolution neural networks for chinese handwriting recognition (2016)
Tsai, C.: Recognizing handwritten Japanese characters using deep convolutional neural networks (2016)
Bluche, T.: Deep neural networks for large vocabulary handwritten text recognition (2015)
Obaid, A.M., El Bakry, H.M., Eldosuky, M.A., Shehab, A.I.: Handwritten text recognition system based on neural network (2016)
AL-Shatnawi, A.M., AL-Salaimeh, S., AL-Zawaideh, F.H., Omar, K.: Offline Arabic text recognition an overview. World Comput. Sci. Inform. Technol. J. 1(5) 184–192, 2011
Parvez, M.T., Mahmoud, S.A.: Offline Arabic handwritten text recognition: a survey. ACM Comput. Surv. 45(2), 23–35 (2013)
Lawgali, A.: A survey on arabic character recognition. Int. J. Signal Process. Image Process. Pattern Recogn. 8(2), 401–426 (2015)
Rabi, M., Amrouch, M., Mahani, Z., Mammass, D.: Recognition of cursive Arabic handwritten text using embedded training based on HMMs. In: Engineering & MIS (ICEMIS) International Conference. IEEE, September 2016. INSPEC Accession Number: 16467172. doi:10.1109/ICEMIS.2016.7745330
Ettaouil, M., Lazaar, M., En-Naimani, Z.: A hybrid ANN/HMM models for Arabic speech recognition using optimal codebook. In: Proceedings of the 8th International Conference on Intelligent Systems: Theories and Applications (SITA). IEEE (2013)
Surwade, S.S.: Speech recognition using HMM/ANN hybrid model. Int. J. Recent Innov. Trends Comput. Commun. 3(6), 4154–4157 (2015). ISSN: 2321-8169
G-Moral, A.I., S-Urena, U., P-Moreno, C., D-Maria, F.: Data balancing for efficient training of hybrid ANN/HMM automatic speech recognition. IEEE Trans. Audio Speech Lang. Proc. 19(3), 468–481, 2011
Mohamed, A., Ramachandran Nair, K.N.: HMM/ANN hybrid model for continuous Malayalam speech recognition. In: Selection and/or Peer-Review Under Responsibility of ICCTSD 2012 (International Conference on Communication Technology and System Design). Elsevier Ltd. (2012)
Trentin, E., Gori, M.: Robust combination of neural networks and hidden Markov models for speech recognition. IEEE Trans. Neural Netw. 14(6), 1519–1531 (2003)
Tagougui, N., Boubaker, H., Kherallah, M., Alimi, A.M.: A hybrid NN/HMM modeling technique for online Arabic handwriting recognition. Int. J. Comput. Linguist. Res. 4(3), 107–118 (2013)
Rabi, M., Amrouch, M., Mahani, Z., Mammass, D.: Evaluation of features extraction and classification techniques for offline handwritten Tifinagh recognition. Glob. J. Comput. Sci. Technol. (USA) C Softw. Data Eng. 16(5) (2016). Version 1.0
Dreuw, P., Doetsch, P., Plahl, C., Ney, H.: Hierarchical hybrid MLP/HMM or rather MLP features for a discriminatively trained Gaussian HMM: a comparison for offline handwriting recognition. In: Proceedings of the 18th IEEE International Conference on Image Processing (ICIP), pp. 3541–3544, September 2011
Espana-Boquera, S., Castro-Bleda, M.J., Gorbe-Moya, J., Zamora-Martinez, F.: Improving offline handwritten text recognition with hybrid HMM/ANN models. IEEE Trans. Pattern Anal. Mach. Intell. 33(4), 767–779 (2011)
Guo, Q., Wang, F., Lei, J., Tu, D., Li, G.: Convolutional feature learning and hybrid CNN-HMM for scene number recognition. J. Neurocomput. Arch. 184(C), 78–90 (2016). Elsevier Science Publishers B.V., Amsterdam
Bluche, T., Ney, H., Kermorvant, C.: Tandem HMM with convolutional neural network for handwritten word recognition. In: Proceedings of the 17th International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 2390–2394. IEEE (2013)
Pechwitz, M., Maddouri, S.S., Maergner, V., Ellouze, N., Amiri, H.: IFN/ENIT – database of handwritten Arabic words. In: CIFED 2002, Hammamet, Tunisia, pp. 129–136 (2002)
Märgner, V., El Abed, H.: ICDAR 2011 - Arabic handwriting recognition competition. In: International Conference on Document Analysis and Recognition, pp. 1444–1448 (2011)
Young, S., et al.: The HTK Book V3.4. Cambridge University Press, Cambridge (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Rabi, M., Amrouch, M., Mahani, Z. (2018). Hybrid HMM/MLP Models for Recognizing Unconstrained Cursive Arabic Handwritten Text. In: Ezziyyani, M., Bahaj, M., Khoukhi, F. (eds) Advanced Information Technology, Services and Systems. AIT2S 2017. Lecture Notes in Networks and Systems, vol 25. Springer, Cham. https://doi.org/10.1007/978-3-319-69137-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-69137-4_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69136-7
Online ISBN: 978-3-319-69137-4
eBook Packages: EngineeringEngineering (R0)