Skip to main content
SpringerLink
Log in

A new representation of shape and its use for high performance in online Arabic character recognition by an associative memory

  • Published:
International Journal of Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

The purpose of this study is to investigate a new representation of shape and its use in handwritten online character recognition by a Kohonen associative memory. This representation is based on the empirical distribution of features such as tangents and tangent differences at regularly spaced points along the character signal. Recognition is carried out by a Kohonen neural network trained using the representation. In addition to the Euclidean distance traditionally used in the Kohonen training algorithm to measure the similarities among feature vectors, we also investigate the Kullback–Leibler divergence and the Hellinger distance, functions that measure distance between distributions. Furthermore, we perform operations (pruning and filtering) on the trained memory to improve its classification potency. We report on extensive experiments using a database of online Arabic characters produced without constraints by a large number of writers. Comparative results show the pertinence of the representation and the superior performance of the scheme.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Al-Emami, S., Usher, M.: On-line recognition of hand-written Arabic characters. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 704-710 (1990)

    Article  Google Scholar 

  2. Al-Sheikh, T.S., El-Taweel, S.G.: Real-time Arabic handwritten character recognition. Pattern Recog. 23(12), 1323-1332 (1990)

    Google Scholar 

  3. Alimi, A.M.: A neuro-fuzzy approch to recognize on-line Arabic handwriting. In: Proceedings of the International Conference on Neural Networks, 3, 1397-1400 (1997)

    Google Scholar 

  4. Alimi, A.M., Ghorbel, O.A.: The analysis of error in an on-line recognition system of Arabic handwritten character. In: Proceedings of the International Conference on Document Analysis and Recognition, 2, 890-893 (1995)

    Google Scholar 

  5. Ben Amara, N.E., Bouslama, F.: Classification of Arabic script using multiple sources of information: state of the art and perspectives. Int. J. Doc. Anal. Recog. 5(4), 195-212 (2003)

    Google Scholar 

  6. Amin, A.: Off line Arabic character recognition-a survey. In: Proceedings of the International Conference Document Analysis Recognition, Germany 1, 596 (1997)

  7. Amin, A.: Off-line Arabic character-recognition: the state of the art. Pattern Recog. 31(5), 517-530 (1998)

    Article  MathSciNet  Google Scholar 

  8. Anquetil, E.: Mod'elisation et reconnaissance par la logique oue: application la lecture automatique en-ligne de l'ecriture manuscrite omni-scripteur. PhD thesis, Universit'e de Rennes I (1997)

  9. Le Bail, E., Mitiche, A.: Quantification vectorielle d'images par le r'eseau neuronal de Kohonen. Traitement du Signal 6(6), 529-539 (1989)

    Google Scholar 

  10. Bouslama, F., Amin, A.: Pen-based recognition system of Arabic character utilizing structural and fuzzy techniques. In: Proceedings of the 2nd International Conference on Knowledge-Based Intelligent Electronic Systems (KES'98), pp. 76-85 (1998)

  11. Domany, E., Hemmen, J.L.v., Schulten, K.: Models of Neural Networks. Springer, Berlin Heidelberg New York (1991)

    MATH  Google Scholar 

  12. Dreyfus, G., Martinez, J., Samuelides, M., Gordon, M., Badran, F.: R'eseaux de neurones: m'ethodologie et applications. Eyrolles (2002)

  13. Duda, P.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)

    MATH  Google Scholar 

  14. El-wakil, M.S., Shoukry, A.A.: On-line recognition of handwritten Arabic character recognition. Pattern Recog. 22(2), 97-105 (1989)

    Article  Google Scholar 

  15. Al Emami, S., Usher, M.: On-line recognition of handwritten Arabic characters. IEEE Trans. Pattern Anal. Mach. Intell. 12(2), 704-710 (1990)

    Google Scholar 

  16. Govindan, V.K., Shivaprasad, A.P.: Character recognition - a review. Pattern Recog. 23(7), 671-683 (1990)

    Article  Google Scholar 

  17. Hart, P.E.: The condensed nearest neighbor rule. IEEE Trans. Inf. 515-516 (1968)

  18. Hasegawa, T., Yasuda, H., Matsumoto, T.: Fast discrete hmm algorithm for on-line handwriting recognition. In: Proceedings of the International Conference on Pattern Recognition, vol. 4, p. 4535, Barcelona, Spain (2000)

  19. Hu, J., Brown, M.K., Turin, W.: HMM based on-line handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 18, 1039-1045 (1996)

    Google Scholar 

  20. Hu, J., Rosenthal, A.S., Brown, M.K.: Combining high-level features with sequential local features for on-line recognition. In: Proceedings of the Italian Image Processing Conference, pp. 647-654, Florence (1997)

  21. Jung, K.C., Kim, H.J.: Korean character recognition using a TDNN and an HMM. Pattern Recog. Lett. 20(6), 551-563 (1999)

    MathSciNet  Google Scholar 

  22. Klassen, T.: Towards neural network recognition of hand-written Arabic letters. Master's thesis. Dalhousie University, Halifax (2001)

  23. Kohonen, T.: Self Organizing Maps. Springer, Berlin Heidelberg New York (1995)

    Google Scholar 

  24. Li, X., Yeung, D.Y.: On-line handwritten alphanumeric character recognition using dominant point strokes. Pattern Recog. 30(1), 675-684 (1998)

    MATH  Google Scholar 

  25. Lippman, R.: An introduction to computing with neural networks. IEEE Signal Process. Mag. 3, 4-22 (1987)

    Google Scholar 

  26. Mahjoub, M.A.: Apport de la modlisation de la dure d'tat dans la reconnaissance en-ligne des caractres Arabes par HMMs. 17th Journe Tunisienne en lectrotechnique et automatique (JTEA'97), pp. 341-348 (1997)

  27. Mahmoud, S.A.: Arabic character-recognition using Fourier descriptors and character contour encoding. Pattern Recog. 27(6), 815-824 (1994)

    Article  MathSciNet  Google Scholar 

  28. Marukatat, S., Sicard, R., Artires, T., Gallinari, P.: A flexible recognition engine for complex on-line hand-written character recognition. In: Proceedings of the 7th International Conference on Document Analysis and Recognition, vol. II, pp. 1048-1051, Edinburgh, UK (2003)

  29. Mezghani, N., Cheriet, M., Mitiche, A.: Combination of pruned Kohonen maps for on-line Arabic characters recognition. In: Proceedings of the 7th International Conference on Document Analysis and Recognition, vol. II, pp. 900-905 (2003)

  30. Mezghani, N., Mitiche, A.: Reconnaissance des caractères manuscrits par r'eseau neuromim'etique de Kohonen. In: Proceedings of the International Conference on Image and Signal Processing, pp. 110-120, Agadir (2001)

  31. Mezghani, N., Mitiche, A.: Reconnaissance des caractères manuscrits par rseau neuromim'etique de Kohonen. Journal Marocain d'Automatique, d'Informatique et de Traitement du Signal, 3(2), 1-12 (2001)

    Google Scholar 

  32. Mezghani, N., Mitiche, A., Cheriet, M.: On-line recognition of handwritten Arabic characters using a Kohonen neural network. In: Proceedings of the 8th International Workshop on Frontiers in Handwriting Recognition, pp. 490-495 (2002)

  33. Mezghani, N., Mitiche, A., Cheriet, M.: Reconnaissance en-ligne de caractères Arabes manuscrits par un r'eseau de Kohonen. Vis. Interface 1, 186-191 (2002)

    Google Scholar 

  34. Miled, H., Cheriet, M., Olivier, C.: Multi-level Arabic handwritten words recognition. In: Proceedings of the International Workshop on Structural and Syntactic Pattern Recognition (SSPR/SPR), pp. 944-951 (1998)

  35. Mitiche, A., Aggarwal, J.K.: Pattern category assignment by neural networks and the nearest neighbors rule. Int. J. Pattern Recog. Artif. Intell. 10, 393-408 (1996)

    Article  Google Scholar 

  36. Plamondon, R.: A model-based segmentation framework for computer processing of handwriting. In: Proceedings of the 11th IAPR International Conference on Pattern Recognition, pp. 303-307 (1992)

  37. Plamondon, R.: Handwriting generation: the delta lognormal theory. In: Proceedings of the 4th International Workshop on Frontiers in Handwriting Recognition, pp. 1-10 (1994)

  38. Ramasubramanian, V., Paliwal, K.K.: An efficient approximation elimination algorithm for fast nearest-neighbour search based on a spherical distance coordinate formulation. Pattern Recog. Lett. 13, 471-480 (1992)

    Google Scholar 

  39. Ritter, H., Schulten, K.: Kohonen's self-organizing maps: exploring their computational capabilities. In: Proceedings of the IEEE International Joint Conference on Neural Networks, pp. 109-116, San Diego (1988)

  40. Sabourin, M., Mitiche, A.: Optical character recognition by a neural network. Neural Netw. 5, 843-852 (1992)

    Article  Google Scholar 

  41. Sabourin, M., Mitiche, A.: Modeling and classification of shape using a Kohonen associative memory. Neural Netw. 6, 275-283 (1993)

    Article  Google Scholar 

  42. Sabourin, M., Mitiche, A., Thomas, D., Nagy, G.: Nn 1 or hand-printed digit recognition using nearest neighbors. In: Proceedings of the 2nd Annual Symposium on Document Analysis and Information Retrieval, pp. 397-412 (1993)

  43. Schenkel, M., Guyon, I., Henderson, D.: On-line script recognition using time delay neural networks and hidden Markov models. In: Proceedings of the International Conference on Acoustics, Speech, and Signal Processing 2, 637-640 (1994)

    Google Scholar 

  44. Scholkopf, B., Smola, A., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10, 1299-1319 (1998)

    Google Scholar 

  45. Seni, G.: Large vocabulary recognition of on-line hand-written cursie words. PhD thesis, The State University of New York at Buffalo (1995)

  46. Su, M.C., Lai, E., Tew, C.Y.: A som-based fuzzy system and its application in handwritten digits recognition. In: Proceedings of the International Symposium on Multimedia Software Engineering, p. 253, Taipei, Taiwan (2000)

  47. Tappert, C.C., Suen, C.Y., Wakahara, T.: The state of the art in on-line handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 12(8), 787-808 (1990)

    Article  Google Scholar 

  48. Yang, L.P., Prasad, R.: Online recognition of hand-written characters using differential angles and structural descriptors. Pattern Recog. Lett. 14(12), 1019-1024 (1993)

    Google Scholar 

  49. Zhu, C.S.: Embedding gestalt laws in Markov random fields. IEEE Trans. Pattern Anal. Mach. Intell. 21(11), 1170-1187 (1999)

    Google Scholar 

  50. Zhu, C.S., Wu, N.Y., Mumford, D.: Minimax entropy principle and its application to texture modeling. Neural Comput. 9(8), (1997)

Download references

Author information

Authors and Affiliations

  1. INRS Énergie, Matériaux et Télécommunications, 800 de la Gauchetière Ouest, Suite 6900, Montréal QC, H5A 1K6, Canada

    N. Mezghani

  2. Laboratoire d'imagerie, de vision et d'intelligence artificielle, École de Technologie Supérieure, 1100 rue Notre-Dame Ouest, Montréal QC, H3C 1K3, Canada

    N. Mezghani

  3. INRS Énergie, Matériaux et Télécommunications, 800 de la Gauchetière Ouest, Suite 6900, Montréal, QC, H5A 1K6, Canada

    A. Mitiche

  4. Laboratoire d'imagerie, de vision et d'intelligence artificielle, École de Technologie Supérieure, 1100 rue Notre-Dame Ouest, Montréal QC, H3C 1K3, Canada

    M. Cheriet

Authors
  1. N. Mezghani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Mitiche
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. Cheriet
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to N. Mezghani.

Additional information

Neila Mezghani receivedan engineering~degree~from~École Supérieure des~Télécommunications, Tunis, Tunisia in 1996. In 1999, she obtained a diplôme d'études approfondies (DEA) in signal processing from {École} Nationale des Ingénieurs de Tunis, Tunisia, and in 2001 a diplôme d'études supérieures sp écialisées in information theory from {École} Supérieure des Télécommunications, Tunis, Tunisia. Since 2002 she has been a Ph.D. student at INRS-EMT, Québec, Canada.~Her research interests include online character recognition, neural networks, and probability density estimation in pattern recognition.

Amar Mitiche holds a Licence Ès Sciences in mathematics from the University of Algiers and a Ph.D. in computer science from the University of Texas at Austin. He is currently a professor at the Institut National de Recherche Scientifique (INRS), Department of Telecommunications, in Montreal, Quebec, Canada. His research is in computer vision. His current interests include image segmentation, motion analysis in monocular and stereoscopic image sequences (detection, estimation, segmentation, tracking, 3D interpretation) with a focus on methods based on level set PDEs, and written text recognition with a focus on neural network methods.

Mohamed Cheriet received his B.Eng. degree in computer science from Université des Sciences et de Technologie d'Alger (Bab Ezouar, Algiers) in 1984 and his M.Sc. and Ph.D., also in computer science, from the University of Pierre et Marie Curie (Paris VI) in 1985 and 1988, respectively. Dr. Cheriet was appointed assistant professor in 1992, associate professor in 1995, and full professor in 1998 in the Department of Automation Engineering, École de technologie supérieure (ETS) of the University of Quebec, in Montreal. Currently, he is the director of LIVIA, the Laboratory for Imagery, Vision and Artificial Intelligence at ETS, and an active member of CENPARMI, the Centre for Pattern Recognition and Machine Intelligence. Professor Cheriet's research focuses on mathematical modeling for signal and image processing, pattern recognition, character recognition, text processing, document analysis and recognition, and perception. He has published more than 100 technical papers in the field. He was a guest editor of the International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI) and the Machine, Perception, and Artificial Intelligence series of books, published by World Scientific, in 1999. He has been serving as associate editor of IJPRAI since 2000. He was the cochair of the 11th and 13th Vision Interface Conferences held respectively in Vancouver in 1998 and in Montreal in 2000. He was also the general cochair of the 8th International Workshop on Frontiers in Handwriting Recognition held in Niagara-on-the-Lake in 2002. Dr. Cheriet is a senior member of IEEE.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mezghani, N., Mitiche, A. & Cheriet, M. A new representation of shape and its use for high performance in online Arabic character recognition by an associative memory. IJDAR 7, 201–210 (2005). https://doi.org/10.1007/s10032-005-0145-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-005-0145-8

Keywords

Search

Navigation