Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Combining RtL and LtR HMMs to recognise handwritten Farsi words of small- and medium-sized vocabularies

Combining RtL and LtR HMMs to recognise handwritten Farsi words of small- and medium-sized vocabularies

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

In this study, a method for holistic recognition of handwritten Farsi words is proposed, which fuses the outputs of right-to-left (RtL) and left-to-right (LtR) hidden Markov models (HMMs). The experimental results on 16,000 images of 200 names of Iranian cities, from the ‘Iranshahr 3’ are presented and compared with those methods using only RtL or LtR models. Experimental results show that the main sources of error are similar beginnings or similar endings of the words. Since RtL and LtR models when dealing with the words behave differently, there is notable error diversity between the two classifiers in such a way that their combination increases the recognition rate. Compared to the RtL-HMM, the product of output scores of the RtL and LtR-HMMs reduces the classification error to about 6, 6 and 3%, for three different feature sets. A subjective error analysis on the results is also provided.

References

    1. 1)
      • 54. Michael, O.: ‘Sensory evaluation of food: statistical methods and procedures’ (CRC Press, New York, NY, USA, 1986), p. 487, ISBN 0-824-77337-3.
    2. 2)
      • 41. Grosicki, E., Carré, M., Brodin, J.M., et al: ‘Results of the RIMES evaluation campaign for handwritten mail processing’. Tenth Int. Conf. Document Analysis and Recognition, Barcelona, 2009, pp. 941945.
    3. 3)
      • 31. Zacher, B., Lidschreiber, M., Cramer, P., et al: ‘Annotation of genomics data using bidirectional hidden Markov models unveils variations in Pol II transcription cycle’, Mol. Syst. Biol., 2014, 10, (12), p. 768.
    4. 4)
      • 43. Azeem, S.A., Ahmed, H.: ‘Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models’, Int. J. Doc. Anal. Recognit., 2013, 16, (4), pp. 399412.
    5. 5)
      • 12. Mozaffari, S., Faez, K., Märgner, V., et al: ‘Lexicon reduction using dots for off-line Farsi/Arabic handwritten word recognition’, Pattern Recognit. Lett., 2008, 29, (6), pp. 724734.
    6. 6)
      • 51. Arani, S.A.A.A., Kabir, E., Ebrahimpour, R.: ‘Handwritten Farsi word recognition using NN-based fusion of HMM classifiers with different types of features’, Int. J. Image Graph., accepted, to be published.
    7. 7)
      • 49. Cruz, R.M.O., Cavalcanti, G.D.C., Ren, T.I.: ‘An ensemble classifier for offline cursive character recognition using multiple feature extraction techniques’. Int. Joint Conf. Neural Networks, Barcelona, Spain, 2010, pp. 18.
    8. 8)
      • 3. Ye, M., Viola, P.A., Raghupathy, S., et al: ‘Learning to group text lines and regions in free form handwritten notes’. Ninth Int. Conf. Document Analysis and Recognition, Curitiba, 2007, vol. 1, pp. 2832.
    9. 9)
      • 9. Masroori, K., Kabir, E.: ‘Handwritten Farsi word recognition using DTW algorithm’, Daneshvar J., 1999, 25, pp. 5968, in Farsi.
    10. 10)
      • 17. Maitra, D.S., Bhattacharya, U., Parui, S.K.: ‘CNN based common approach to handwritten character recognition of multiple scripts’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 10211025.
    11. 11)
      • 35. Kuncheva, L.I.: ‘Combining pattern classifiers: methods and algorithms’ (Wiley-Interscience, Hoboken, NJ, USA, 2014, 2nd edn.).
    12. 12)
      • 19. Yang, W., Jin, L., Xie, Z., et al: ‘Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 551555.
    13. 13)
      • 2. Pal, U., Belaïd, A., Choisy, C.: ‘Touching numeral segmentation using water reservoir concept’, Pattern Recognit. Lett., 2003, 24, (1–3), pp. 261272.
    14. 14)
      • 44. Verma, B., Gader, P., Chen, W.: ‘Fusion of multiple handwritten word recognition techniques’, Pattern Recognit. Lett., 2001, 22, (9), pp. 991998.
    15. 15)
      • 5. Steinherz, T., Rivlin, E., Intrator, N.: ‘Off-line cursive script word recognition: a survey’, Int. J. Doc. Anal. Recognit., 1999, 2, (2), pp. 90110.
    16. 16)
      • 23. Graves, A., Schmidhuber, J.: ‘Offline handwriting recognition with multidimensional recurrent neural networks’. Advances in Neural Information Processing Systems, Vancouver, Canada, 2008, vol. 21.
    17. 17)
      • 13. Davoudi, H., Cheriet, M., Kabir, E.: ‘Lexicon reduction of handwritten Arabic subwords based on the prominent shape regions’, Int. J. Doc. Anal. Recognit., 2016, 19, (2), pp. 139153.
    18. 18)
      • 4. Govindaraju, V., Xue, H.: ‘Fast handwriting recognition for indexing historical documents’. Proc. First Int. Workshop Document Image Analysis for Libraries, Palo Alto, 2004, pp. 314320.
    19. 19)
      • 40. Pechwitz, M., Maddouri, S.S., Märgner, V., et al: ‘IFN/ENIT -database of handwritten Arabic words’. Colloque Int. Francophone Surl'Ecrit et le Doucement, Hammamet, Tunisia, 2002, pp. 129136.
    20. 20)
      • 42. Burger, T., Kessentini, Y., Paquet, T.: ‘Dempster–Shafer based rejection strategy for handwritten word recognition’. Int. Conf. Document Analysis and Recognition, Beijing, 2011, pp. 528532.
    21. 21)
      • 14. Frinken, V., Uchida, S.: ‘Deep BLSTM neural networks for unconstrained continuous handwritten text recognition’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 911915.
    22. 22)
      • 21. Dehghan, M., Faez, K., Ahmadi, M., et al: ‘Unconstrained Farsi handwritten word recognition using fuzzy vector quantization and hidden Markov models’, Pattern Recognit. Lett., 2001, 22, (2), pp. 209214.
    23. 23)
      • 39. Kessentini, Y., Burger, T., Paquet, T.: ‘Evidential combination of multiple HMM classifiers for multi-script handwriting recognition’, Comput. Intell. Knowl.-Based Syst. Des., 2010, 6178, pp. 445454.
    24. 24)
      • 29. Zheng, Y., Cai, Y., Zhong, G., et al: ‘Stretching deep architectures for text recognition’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 236240.
    25. 25)
      • 53. Mohamed, M., Gader, P.: ‘Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation based dynamic programming techniques’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (5), pp. 548554.
    26. 26)
      • 48. Chim, Y.C., Kassim, A.A., Ibrahim, Y.: ‘Dual classifier system for hand printed alphanumeric character recognition’, Pattern Anal. Appl., 1998, 1, (3), pp. 155162.
    27. 27)
      • 46. Salimi, H., Giveki, D.: ‘Farsi/Arabic handwritten digit recognition based on ensemble of SVD classifiers and reliable multi-phase PSO combination rule’, Int. J. Doc. Anal. Recognit., 2013, 16, (4), pp. 371386.
    28. 28)
      • 22. Khorsheed, M.S.: ‘Recognizing handwritten Arabic manuscripts using a single hidden Markov model’, Pattern Recognit. Lett., 2003, 24, (14), pp. 22352242.
    29. 29)
      • 50. Abed, H., Märgner, V.: ‘A framework for the combination of different Arabic handwritten word recognition systems’. Int. Conf. Pattern Recognition, Istanbul, Turkey, 2010, pp. 19041907.
    30. 30)
      • 45. Hull, J.J.: ‘A database for handwritten text recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 1994, 16, (5), pp. 550554.
    31. 31)
      • 27. Liu, X., Tang, B., Wang, Z., et al: ‘Chart classification by combining deep convolutional networks and deep belief networks’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 801805.
    32. 32)
      • 30. Arani, S.A.A.A., Kabir, E., Ebrahimpour, R.: ‘Farsi handwritten word recognition using image gradient and hidden Markov model’. Ninth Conf. Machine Vision and Image Processing, Tehran, Iran, 2015, in Farsi.
    33. 33)
      • 11. Bayesteh, E., Ahmadifard, A., Khosravi, H.: ‘A lexicon reduction method based on clustering word images in offline Farsi handwritten word recognition systems’. Seventh Iranian Conf. Machine Vision and Image Processing (MVIP), Tehran, Iran, 2011.
    34. 34)
      • 18. Kim, I., Xie, X.: ‘Handwritten Hangul recognition using deep convolutional neural networks’, Int. J. Doc. Anal. Recognit., 2015, 18, (1), pp. 113.
    35. 35)
      • 47. Frinken, V., Peter, T., Fischer, A., et al: ‘Improved handwriting recognition by combining two forms of hidden Markov models and a recurrent neural network’, Computer Analysis of Images and Patterns, Berlin, Heidelberg, Germany, 2009 (LNCS, 5702), pp. 189196.
    36. 36)
      • 16. Graves, A., Liwicki, M., Fernández, S., et al: ‘A novel connectionist system for unconstrained handwriting recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (5), pp. 855868.
    37. 37)
      • 6. Lu, Y., Shridhar, M.: ‘Character segmentation in handwritten words – an overview’, Pattern Recognit., 1996, 29, (1), pp. 7796.
    38. 38)
      • 7. Madhvanath, S., Govindaraju, V.: ‘The role of holistic paradigms in handwritten word recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (2), pp. 149164.
    39. 39)
      • 38. Huang, Y.S., Suen, C.Y.: ‘A method of combining multiple experts for the recognition of unconstrained handwritten numerals’, IEEE Trans. Pattern Anal. Mach. Intell., 1995, 17, (1), pp. 9094.
    40. 40)
      • 32. Ejlali, N., Pezeshk, H.: ‘A bidirectional hidden Markov model in linear memory’, J. Stat. Sci., 2009, 2, (2), pp. 131148.
    41. 41)
      • 26. Abandah, G.A., Graves, A., Al-Shagoor, B., et al: ‘Automatic diacritization of Arabic text using recurrent neural networks’, Int. J. Doc. Anal. Recognit., 2015, 18, (2), pp. 183197.
    42. 42)
      • 28. Harley, A.W., Ufkes, A., Derpanis, K.G.: ‘Evaluation of deep convolutional nets for document image classification and retrieval’. 13th Int. Conf. Document Analysis and Recognition, Tunis, 2015, pp. 991995.
    43. 43)
      • 8. Choisy, C., Belaïd, A.: ‘Cross-learning in analytic word recognition without segmentation’, Int. J. Doc. Anal. Recognit., 2002, 4, (4), pp. 281289.
    44. 44)
      • 24. Chherawala, Y., Roy, P.P., Cheriet, M.: ‘Combination of context-dependent bidirectional long short-term memory classifiers for robust offline handwriting recognition’, Pattern Recognit. Lett., 2017, 90, pp. 5864.
    45. 45)
      • 37. Günter, S., Bunke, H.: ‘Ensembles of classifiers for handwritten word recognition’, Int. J. Doc. Anal. Recognit., 2003, 5, (4), pp. 224232.
    46. 46)
      • 34. Pezeshk, H., Naghizadeh, S., Malekpour, S. A., et al: ‘A modified bidirectional hidden Markov model and its application in protein secondary structure prediction’. Second Int. Conf. Advanced Computer Control (ICACC), Shenyang, China, 2010.
    47. 47)
      • 10. Arani, S.A.A.A., Kabir, E.: ‘Neural networks combination based on negative correlation learning for handwritten Farsi word recognition’. 12th Conf. Intelligent Systems, Bam, Kerman, Iran, 2014, in Farsi.
    48. 48)
      • 25. Chherawala, Y., Roy, P.P., Cheriet, M.: ‘Feature set evaluation for offline handwriting recognition systems: application to the recurrent neural network model’, IEEE Trans. Cybern., 2016, 46, (12), pp. 28252836.
    49. 49)
      • 36. Xu, L., Krzyzak, A., Suen, C.Y.: ‘Methods of combining multiple classifiers and their applications to handwriting recognition’, IEEE Trans. Syst. Man Cybern., 1992, 22, (3), pp. 418435.
    50. 50)
      • 15. Marti, U.V., Bunke, H.: ‘The IAM-database: an English sentence database for offline handwriting recognition’, Int. J. Doc. Anal. Recognit., 2002, 5, (1), pp. 3946.
    51. 51)
      • 52. Azmi, R., Kabir, E.: ‘A new segmentation technique for omnifont Farsi text’, Pattern Recognit. Lett., 2001, 22, (2), pp. 97104.
    52. 52)
      • 20. Dehghan, M., Faez, K., Ahmadi, M., et al: ‘Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM’, Pattern Recognit., 2001, 34, (5), pp. 10571065.
    53. 53)
      • 1. Vajda, S., Roy, K., Pal, U., et al: ‘Automation of Indian postal documents written in Bangla and English’, Int. J. Pattern Recognit. Artif. Intell., 2009, 23, (8), pp. 15991632.
    54. 54)
      • 33. Kadim, A., Lazrek, A.: ‘Bidirectional HMM-based Arabic POS tagging’, Int. J. Speech Technol., 2016, 19, (2), pp. 303312.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0645
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0645
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address