Special Issue on The Mexican Conference on Pattern Recognition; Guest Editors: José Fco. Martínez-Trinidad (National Institute of Astrophysics, Optics and Electronics, Mexico), Jesús Ariel Carrasco-Ochoa (National Institute of Astrophysics, Optics and Electronics, Mexico), Víctor Ayala-Ramírez (University of Guanajuato, Mexico) and José Arturo Olvera-López (Autonomous University of Puebla (BUAP), Mexico)No Access

Recognition of Cursive Arabic Handwritten Text Using Embedded Training Based on Hidden Markov Models

Mouhcine Rabi

Laboratory IRF-SIC, Faculty of Sciences, Ibn Zohr University Agadir, Morocco

E-mail Address: mouhcineh@gmail.com

Corresponding author.

Search for more papers by this author

Mustapha Amrouch

Laboratory IRF-SIC, Faculty of Sciences, Ibn Zohr University Agadir, Morocco

E-mail Address: m.amrouch@uiz.ac.ma

Search for more papers by this author

, and

Zouhir Mahani

High School of Technology, Ibn Zohr University Agadir, Morocco

E-mail Address: zouhir.mahani@uiz.ac.ma

Search for more papers by this author

https://doi.org/10.1142/S0218001418600078Cited by:20 (Source: Crossref)

Abstract

This paper presents a system for offline recognition of cursive Arabic handwritten text based on Hidden Markov Models (HMMs). The proposed work reports an effective method taking into account the context of character by applying an embedded training-based HMMs to perform and enhance the character models. The system is analytical without explicit segmentation; extracted features preceded by baseline estimation are statistical and structural to integrate both the peculiarities of the text and the pixel distribution characteristics of the word image. The experiments are done on benchmark IFN/ENIT database. The proposed work shows the effectiveness of using embedded training-based HMMs for enhancing the recognition rate, and the obtained results are promising and encouraging.

Keywords:

References

1. A. K. Abdul Hassan and M. S. Kadhm, Handwriting word recognition based on neural networks, Int. J. Appl. Eng. Res. 10 (22) (2015) 43120–43124. Google Scholar
2. I. Ahmad, G. A. Fink and S. A. Mahmoud, Improvement in sub-character HMM model based Arabic text recognition, in 2014 14th Int. Conf. Frontiers in Handwriting Recognition. Google Scholar
3. J. Alabodi and X. Li, An effective approach to offline Arabic handwriting recognition, Int. J. Artificial Intell. Appl. 4 (6) (2013) 1. Google Scholar
4. J. H. Alkhateeb, O. Pauplin, J. Ren and J. Jiang, Performance of hidden Markov model and dynamic Bayesian network classifiers on handwritten Arabic word recognition, Knowl.-Based Syst. 24 (2011) 680–688. Crossref, Web of Science, Google Scholar
5. J. H. AlKhateeb, J. Ren, J. Jiang and H. Al-Muhtaseb, Offline handwritten arabic cursive text recognition using hidden markov models and re-ranking, Patt. Recognit. Lett. 32 (8) (2011) 1081–1088. Crossref, Web of Science, Google Scholar
6. A. M. AL-Shatnawi, S. AL-Salaimeh, F. H. AL-Zawaideh and K. Omar, Offline arabic text recognition an overview, World Comput. Sci. Inform. Technol. J. 1 (5) (2011) 184–192. Google Scholar
7. N. Arica and F. T. Yarman-Vural, Optical character recognition for cursive handwriting, IEEE Trans. Pattern Anal. Mach. Intell. 24 (6) (2002) 801–813. Crossref, Web of Science, Google Scholar
8. S. G. Azar, and H. Seyedarabi, Continuous hidden Markov model based dynamic Persian sign language recognition, IEEE Electrical Eng. Conf. (ICEE), 2016. Google Scholar
9. S. Azeem and H. Ahmed, Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models, Int. J. Doc. Anal. Recognit. 16 (4) (2013) 399–412. Crossref, Web of Science, Google Scholar
10. A.-L. Bianne-Bernard, F. Menasri, L. Likforman-Sulem, C. Mokbel and C. Kermorvant, Variable length and context-dependent HMM letter form models for Arabic handwritten word recognition, in Document Recognition and Retrieval Conf. (DRR). Google Scholar
11. T. Bluche, Deep neural networks for large vocabulary handwritten text recognition, Computers and Society [cs.CY]. Universit e Paris Sud — Paris XI, 2015. English. $<$ NNT : 2015PA112062 $>$ . $<$ tel-01249405 $>$ . Google Scholar
12. T. Bluche, H. Ney and C. Kermorvant, The LIMSI handwriting recognition system for the HTRtS 2014 contest, in Int. Conf. Document Analysis and Recognition (ICDAR), 2015. Google Scholar
13. T. Bluche, H. Ney and C. Kermorvant, Tandem HMM with convolutional neural network for handwritten word recognition, in 38th Int. Conf. Acoustics Speech and Signal Process. (ICASSP2013) (Vancouver, BC, Canada, 2013), pp. 2390–2394. Google Scholar
14. H. Bunke, Recognition of Cursive Roman Handwriting - Past, Present and Future, in Proc. 7th Int. Conf. Document Analysis and Recognition, Vol. 1, pp. 448–459, August 2003. Google Scholar
15. Y. Chherawala, P. P. Roy and M. Cheriet, Context-dependent BLSTM models. Applications to offline handwriting recognition, in 2014 IEEE Int. Conf. Image Process. (ICIP). Google Scholar
16. C. Choisy and A. Belaïd, Apprentissage croisé en reconnaissance analytique de l’écriture manuscrite, Colloque International Francophone Sur l’écrit et le Document 2000. Google Scholar
17. N. Cirera, A. Fornés and J. Lladós, Hidden Markov model topology optimization for handwriting recognition, in 2015 IEEE 13th Int. Conf. Document Analysis and Recognition (ICDAR), August 2015. Google Scholar
18. H. El Abed and V. Margner, Icdar 2009-arabic handwriting recognition competition, Int. J. Doc. Anal. Recognit. 14 (1) (2011) 3–13. Crossref, Web of Science, Google Scholar
19. El Moubtahij Hicham, H. Akram and K. Satori, Using features of local densities statistics and HMM toolkit (HTK) for offline Arabic handwriting text recognition, 2016. Google Scholar
20. R. R. EL-Hajj, L. L. Sulem and C. Mokbel, Combining slanted-frames classifiers for improved HMM-based arabic handwriting recognition, IEEE Trans. Pattern Anal. Machine Intell. 2009. Web of Science, Google Scholar
21. M. Elleuch, N. Tagougui and M. Kherallah, Towards unsupervised learning for Arabic handwritten recognition using deep architectures, in Neural Information Process. Lecture Notes in Computer Science, Vol. 9489 (Springer, 2015), pp. 363–372. Crossref, Google Scholar
22. M. Elleucha, R. Maalejb and M. Kherallahc, A new design based-SVM of the CNN classifier architecture with dropout for offline arabic handwritten recognition. Procedia Computer Science, Int. Conf. Comput. Sci. 2016, (ICCS 2016) 6–8 June 2016, San Diego, California, USA, Vol. 80, pp. 1712–1723. Google Scholar
23. F. Farooq, V. Govindaraju and M. Perrone, Pre-processing methods for handwritten Arabic Documents, (ICDAR’05) Seoul, 2005, pp. 267–271. Google Scholar
24. H. Fujisawa, Forty years of research in character and document recognition — an industrial perspective, Pattern Recognit. 41 (8) (2008) 2435–2446. Crossref, Web of Science, Google Scholar
25. M. Jaderberg, K. Simonyan, A. Vedaldi and A. Zisserman, Synthetic data and artificial neural networks for natural scene text recognition, arXiv preprint arXiv:1406.2227, 2014. Google Scholar
26. K. Jayech, M. Mahjoub and N. B. Amara, Arabic Handwritten Word Recognition based on Dynamic Bayesian Network, 2016. Google Scholar
27. P. M. Kamble and R. S. Hegadi, Deep neural network for handwritten Marathi character recognition, Int. J. Imaging Robotic. 17 (1) (2017) 95–107. Google Scholar
28. Y. Kessentini, T. Paquet and A. Ben Hamadou, Off-line handwritten word recognition using multistream hidden Markov models, Patt. Recognit. Lett. 31 (2010) 60–70. Crossref, Web of Science, Google Scholar
29. M. Kozielski, P. Doetsch and H. Ney, Improvements in RWTH’s system for off-line handwriting recognition, in Int. Conf. Document Analysis and Recognition (ICDAR2013), pp. 935–939 (2013). Google Scholar
30. A. Lawgali, A survey on arabic character recognition, Int. J. Signal Process. Image Process. Pattern Recognit. 8 (2) (2015) 401–426. Google Scholar
31. A. Lawgali, M. Angelova and A. Bouridane, A framework for arabic handwritten recognition based on segmentation, Int. J. Hybrid Inf. Technol. 7 (5) (2014) 413–428. Crossref, Google Scholar
32. Y. Le Cun, L. Bottou and Y. Bengio, Reading checks with multilayer graph transformer networks, in Int. Conf. Acoustics, Speech, and Signal Process. 1997. Google Scholar
33. Q. Li, W. An, A. Zhou and L. Ma, Recognition of offline handwritten Chinese characters using the tesseract open source OCR engine, 2016 8th Int. Conf. Intelligent Human-Machine Systems and Cybernetics (IHMSC), IEEE December 2016. Google Scholar
34. L. M. Lorigo and V. Govindaraju, Offline arabic handwriting recognition: A survey, IEEE Trans. Pattern Anal. Mach. Intell. 28 (5) (2006) 712–724. Crossref, Web of Science, Google Scholar
35. R. Maalej, N. Tagougui and M. Kherallah, Arabic handwriting recognition with dropout applied in deep recurrent neural networks, in 2016 12th IAPR Workshop Document Analysis Systems (DAS), doi: 10.1109/DAS.2016.49. Google Scholar
36. A. Maqqor, A. Halli, K. Satori and H. Tairi, Off-line recognition handwriting combination of mutiple classifiers, in 3rd Int. IEEE Colloquium on Information Science and Technology (IEEE CIST’14), October 2014. Google Scholar
37. V. Margner and H. Abed, Icdar 2011-arabic handwriting recognition competition, in 2011 Int. Conf. Document Analysis and Recognition (ICDAR), pp. 1444–1448. Google Scholar
38. V. Margner and H. E. Abed, Icfhr 2010-arabic handwriting recognition competition, in 2010 Int. Conf. Frontiers in Handwriting Recognition (ICFHR), pp. 709–714. Google Scholar
39. V. Märgner and H. El Abed, Arabic handwriting recognition competition, in Int. Conf. Document Analysis and Recognition (ICDAR), 2011. Google Scholar
40. O. Morillot, New baseline correction algorithm for text-line recognition with bidirectional recurrent neural networks, J. Electron. Imaging 22 (2) ( Apr–Jun 2013) 023028. Crossref, Web of Science, Google Scholar
41. A. M. Obaid, H. M. El Bakry, M. A. Eldosuky and A. I. Shehab, Handwritten text recognition system based on neural network, Int. J. Adv. Res. Comput. Sci. Technol. 4 (1) (2016) (Jun.–Mar. 2016). Google Scholar
42. S. Pang and X. Yang, Deep convolutional extreme learning machine and its application in handwritten digit classification, Comput. Intell. Neurosci. Published online 2016 Aug 17. DOI: 10.1155/2016/3049632. Google Scholar
43. M. T. Parvez and S. A. Mahmoud, Offline Arabic handwritten text recognition: A survey, ACM Comput. Surv. (CSUR) 45 (2) (2013) Article No. 23. Crossref, Web of Science, Google Scholar
44. M. T. Parvez and A. M. Sabri, Arabic handwriting recognition using structural and syntactic pattern attributes, Pattern Recognit. 46 (2013) 141–154. Crossref, Web of Science, Google Scholar
45. M. Pechwitz and V. Maergner, Hmm based approach for handwritten arabic word recognition using the ifn/enit database, in Proc. Seventh Int. Conf. Document Analysis and Recognition, pp. 890–894, 2003. Google Scholar
46. M. Pechwitz, S. S. Maddouri, V. Märgner, N. Ellouze, H. Amiri et al., Ifn/enit-database of handwritten Arabic words. Citeseer. Google Scholar
47. M. Pechwitz, S. S. Maddouri, V. Maergner, N. Ellouze and H. Amiri, IFN/ENIT — Database of handwritten Arabic WordsCIFED 2002, Hammamet, Tunisia (2002), pp. 129–136. Google Scholar
48. L. R. Rabiner, A tutorial on Hidden Markov Models and selected applications in speech recognition, Proc. IEEE 77 (2) (1989) 257–286. Crossref, Web of Science, Google Scholar
49. B. Su, X. Ding, L. Peng and C. Liu, A novel baseline independent feature set for Arabic handwriting recognition, in 2013 12th Int. Conf. Document Analysis and Recognition (ICDAR), pp. 1250–1254. Google Scholar
50. A. Vinciarelli, S. Bengio and H. Bunke, Offline recognition of unconstrained handwritten texts using HMMs and statistical language models, IEEE Trans. Pattern Anal. Mach. Intell. 26 (6) (2004) 709–720. Crossref, Web of Science, Google Scholar
51. D. Xiang, H. Yan, X. Chen and Y. Cheng, Offline Arabic handwriting recognition system based on HMM, 978-1-4244-5539-3/10/$26.00 © 2010 IEEE. Google Scholar
52. H. Xue and V. Govindaraju, Hidden Markov Models combining discrete symbols and continuous attributes in handwriting recognition, IEEE Trans. Pattern Anal. Mach. Intell. 28 (3) (2006) 458–462. Crossref, Web of Science, Google Scholar
53. S. Young et al., The HTK Book V3.4 (Cambridge University Press, Cambridge UK, 2006). Google Scholar