JACIII Vol.13 No.5 pp. 512-519
doi: 10.20965/jaciii.2009.p0512


A Granular Framework for Recognition of Arabic Handwriting

Mokhtar Beldjehem

Sainte Anne University, 1589 Walnut Street Halifax, Nova Scotia, B3H 3S1, Canada

September 19, 2008
February 21, 2009
September 20, 2009
granular Arab handwriting recognition, fuzzy and soft computing, morphological analysis, cooperative morphological-guided recognition, approximate fault tolerant recognizer
We propose a novel cognitively motivated unifying framework for Arabic handwriting recognition that takes into account the nature of the human reading process of Arabic handwriting. This Modular Granular Architecture tackles the problem by observing Arabic handwriting from both perceptual and linguistic points of view and hence analyzes the underlying input signal from different granularity levels. It is based on three levels of abstraction: a low granularity level that uses perceptual features called global visual indices, a medium granularity level that is the conventional recognition stage and a high granularity level that consists on morphological analysis dedicated to segmentation/recognition. The original idea is the effective use of Arabic word's morphology in the recognition not only in post-processing. This architecture carries well around the Arabic word's morphology, as typically in Arabic, the Arabic word's morphology is by excellence the logical structure (even semantic) of a given Arabic word, whereas the visual data constitute the physical geometric (topological) structure of a given word. We need to integrate both of them for an effective cooperative recognition of Arabic Handwriting. This framework subsumes the lexicon-driven approaches; in that it can recognize a word that does not exist within the lexicon.
Cite this article as:
M. Beldjehem, “A Granular Framework for Recognition of Arabic Handwriting,” J. Adv. Comput. Intell. Intell. Inform., Vol.13 No.5, pp. 512-519, 2009.
Data files:
  1. [1] S. S. Hyder and A. Khoujah, “Character Recognition of Cursive Scripts,” IEA/AIE 2, pp. 1146-1150, 1988.
  2. [2] R. M. Bozinovic and S. H. Srihari, “Off-line cursive script word recognition,” IEEE Trans. PAMI 11, No.1, pp. 68-83, 1989.
  3. [3] C. L. Liu, S. Jaeger, and M. Nakagawa, “Online recognition of Chinese characters: the state of the art,” IEEE Trans. On PAMI 26, No.2, pp. 198-213, 2004.
  4. [4] R. Plamondon and S. N. Srihari, “On-line and off-line handwriting: A comprehensive survey,” IEEE Transaction on Pattern Analysis and Machine Intelligence 22, No.1, pp. 63-84, 2000.
  5. [5] J. C. Simon, “La Reconnaissance des Formes par Algorithmes,” Edition Masson, p. 252, 1985.
  6. [6] J. C. Simon, “From Pixels to Features,” North Holland, Amsterdam, 1989.
  7. [7] J. C. Simon, “Off-line cursive word recognition,” Proc. IEEE 80, No.7, pp. 1150-1161, 1992.
  8. [8] C. Y Suen, R. Legault, C. P. Nadal, M. Cheriet, and L. Lam, “Building a new generation of handwriting recognition systems,” Pattern Recognition, Letters 14, No.4, pp. 303-315, 1993.
  9. [9] C. C Tappert, C. Y. Suen, and T. Wakahara, “The state of the art in on-line handwriting recognition,” IEEE Trans. On PAMI 12, No.8, pp. 787-808, 1990.
  10. [10] A. Amin, A. Kaced, J.-P Haton, and R. Mohr, “Handwritten Arabic Character recognition by the IRAC system,” in Proc. Int. Conf. on Pattern Recognition, Miami, Florida, USA, pp. 729-731, 1980.
  11. [11] A. Amin, “Recognition of Handwritten Arabic Script and Sentences,” in Proc. IAPR 2, Montreal, pp. 1055-1057, 1984.
  12. [12] B. Al-Badr and S. Mahmoud, “Survey and bibliography of Arabic Optical text recognition,” Signal Processing, Vol.41, pp. 49-77, 1995.
  13. [13] M. Beldjehem, “Visual Processing of Arabic Handwriting: Challenges and Future directions,” in Proc. SACH 06, Maryland, 2006.
  14. [14] L. M. Lorigo and V. Govindarraju, “Offline Arabic handwriting recognition: a survey,” IEEE Trans. PAMI 28, No.5, pp. 712-724, 2006.
  15. [15] I. S. I. Abuhaiba and P. Ahmed, “Restoration of temporal information in off-line Arabic handwriting,” Pattern Recognition, Vol.26, No.7, pp. 1009-1017, 1993.
  16. [16] I. S. I Abuhaiba, A. M. Sabri, and R. J Green, “Recognition of Handwritten Cursive Arabic Characters,” IEEE Trans. Pattern Anal. Mach. Intell, Vol.16, No.6, pp. 664-672, 1994.
  17. [17] H. Almuallim and S. Yamaguchi, “A method for recognition of Arabic cursive handwriting,” IEEE Trans. Pattern Analysis Machine Intelligence 9, No.5, pp. 715-722, Sep., 1987.
  18. [18] S. Al-Emami and M. Usher, “On-line recognition of handwritten Arabic characters 12,” No.7, pp. 704-710, Sep. 1990.
  19. [19] T. S. Al-sheikh and S. G. El-Taweel, “Real-time Arabic handwritten character recognition,” Pattern Recognition 23, No.12, pp. 1323-1332, 1990.
  20. [20] A. Amin, “Recognition of printed Arabic text based on global features and decision tree learning techniques,” Pattern Recognition 33, No.8, pp. 1309-1323, 2000.
  21. [21] L. Souici-Meslati and M. Sellami, “A Hybrid Neuro-Symbolic Approach for Arabic Handwritten Word Recognition,” JACIII, Vol.10, No.1, pp. 17-25, 2006.
  22. [22] Y. Al-Ohali, M. Cheriet, and C. Suen, “Databases for recognition of handwritten Arabic cheques,” Pattern Recognition, 36, pp. 111-121, 2003.
  23. [23] J. J. Hull, “A Database for handwritten text recognition research,” IEEE Trans. PAMI 16, pp. 550-554, 1994.
  24. [24] M. Pechwitz, S Snoussi-Maddouri, V. M”agner, N. Ellouse, and H. Amiri, “IFN/ENIT database of handwritten Arabic words,” Proc. Colloque Francophone Int. sur l’Ecrit et le Document, Hammamet, Tunisia, pp. 129-136, 2002.
  25. [25] D. Marr, “Vision, A Computational Investigation into Human Representation and Processing of Visual Information,” Freeman W. H. and Company, San Fransisco, 1982.
  26. [26] S. K. Pal and A. Ghosh (Ed.), “Soft Computing in Image Processing,” Physica-Verlag, Heidelberg, 2000.
  27. [27] W. J. M. Kickert and H. Koppelar, “Application of fuzzy set theory to syntactic pattern recognition of handwritten capitals,” IEEE Trans. Syst. Man Cybernet. 6, pp. 148-151, Feb. 1976.
  28. [28] P. Siy and C. S. Chen, “Fuzzy logic for handwritten character recognition,” IEEE Trans. Syst. Man Cybernet. 4, pp. 570-575, Nov. 1974.
  29. [29] L. A. Zadeh, “Fuzzy sets,” Info. Control 89, pp. 338-353, 1965.
  30. [30] L. A. Zadeh, “Toward a theory of fuzzy systems,” in R. E. Kalman and N. Declaris (Eds.), Aspects of Network and System Theory, Holt, Rinehart and Winston, New York, pp. 209-245, 1971.
  31. [31] L. A. Zadeh, “Fuzzy logic neural networks, and soft computing,” Communications of the ACM 37, pp. 77-84, 1994.
  32. [32] L. A. Zadeh, “Soft Computing, Fuzzy Logic and Recognition Technology,” In Proc. IEEE Int. Conf. Fuzzy Syst., Anchorage, AK, pp. 1678-1679, 1998.
  33. [33] M. Beldjehem, “Un apport àa la conception des systèemes hybrides neuro-flous par algorithmes d’approximation d’éequations de relations floues en MIN-MAX : le systèeme Fennec,” Ph.D. Thesis in Computer Science and Software Engineering (Artificial Intelligence), Universitée de la Mediterannéee (Aix-Marseille II), Marseille, 1993 (in French).
  34. [34] M. Beldjehem, “Fennec, un géenéerateur de systèemes neuro-flous,” in Proc. les Actes des Applications des Ensembles Flous, Nimes, France, pp. 209-218, 1993 (in French).
  35. [35] M. Beldjehem, “Le systèeme fennec,” in Electronic BUSEFAL 55, pp. 95-104, 1993 (in French).
  36. [36] M. Beldjehem, “The fennec system,” in Proc. ACM Symposium on Applied Computing (SAC), Track on fuzzy logic in Applications, pp. 126-130, Phoenix, AZ, March, 1994.
  37. [37] M. Beldjehem, “Machine Learning based on the possibilistic-neuro hybrid approach: design and implementation.” in Electronic BUSEFAL 87, pp. 95-104, 2002.
  38. [38] M. Beldjehem, “Learning IF-THEN Fuzzy Weighted Rules,” in Proc. Int. Conf. of Computational intelligence, Nicosia, North Cyprus, 2002.
  39. [39] M. Beldjehem, “Validation of Hybrid MinMax Fuzzy--Neuro Systems,” in Proc. Int. Conf. of NAFIPS, Montreal, 2006.
  40. [40] M. Beldjehem, “Towards a Validation Theory of Hybrid MinMax Fuzzy-Neuro Systems,” in Proc. of the WSEAS, Int. Conf., Sofia, 2008.
  41. [41] M. Beldjehem, “Towards a Validation Theory of Hybrid MinMax Fuzzy-Neuro Systems,” in Proc. of the CIMSA Int. Conf., Istambul, 2008.
  42. [42] M. Miled and al. 1998. “Multi-level Arabic Handwritten Words Recognition.” in Proc. SSPR/SPR, Sydney, NSW, Australia, pp. 944-951.
  43. [43] M. Allam, “Segmentation versus segmentation-free for recognizing Arabic text,” Proc. SPIE 2422, pp. 228-235, 1995.
  44. [44] A. Allam, “Segmentation versus segmentation-free for recognizing Arabic text,” Proc. SPIE 2422, pp. 228-235, 1995.
  45. [45] A. Cheung, M. Bennamoun, and N. W. Bergmann, “An Arabic optical character recognition system using recognition-based segmentation,” Pattern Recognition, 34, No.2, pp. 215-233, 2001.
  46. [46] Al-Sughaiyer and I. A. Al-Kharash, “Arabic Morphological Analysis Techniques,” J. of the Amer. Soc. For Inf. Sc. And Tech. 55, No.3, pp. 189-213, 2004.
  47. [47] S. Mordechay, H. Lim, and W. Shoaf, “The utilization of fuzzy sets in the recognition of imperfect strings,” Fuzzy Sets and Systems, 49, pp. 331-337, 1992.
  48. [48] E. Ukkonen, “Algorithms for approximate string matching,” Information and Control 64, pp. 100-118, 1985.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 19, 2024