Toward Distributed Cursive Writing OCR Systems Based on a Combination of Complementary Approaches

Chapter

Abstract

Large amounts of cursive writing documents are still waiting to be computerized for several and different purposes. These documents are in general of medium to low quality; hence they require a sophisticated recognition algorithm capable of properly extracting the correct text from low quality cursive documents. The Dynamic Time Warp (DTW) algorithm is among the most effective algorithms for cursive writing optical character recognition (OCR). However, the DTW is a rather complex task requiring extensive computational capabilities, which hinders its commercial deployment on nonspecialized stand alone machines. Volunteer grids, such as XtremWeb and BOINC, provide viable infrastructures to speed up the DTW execution time. Recent experiments conducted on the Scientific Research Tunisian Grid (SRTG), an XtremWeb volunteer grid, confirmed this claim and showed a very tangible speedup along very high recognition rates. Such infrastructures present several practical advantages, such as the possibility of noncondemnation of the involved computers and the possibility of their simultaneous use by different users and/or applications. Unfortunately, volunteer grid infrastructures are inherently unable to guarantee the continuous availability of the stored data and, more importantly, the engaged processing capacities. Any involved computer may renegade and depart from the system at will, which consequently affects the application performance. Agent technology can be exploited here to solve the problem. In this chapter, we propose a service-oriented grid architecture (SOGA) based on the integration of both grid and agent technologies. An analytical study is conducted to ascertain and evaluate the key performance parameters of our proposed SOGA. The results confirm that our proposal provides a solid and viable solution for the large scale recognition of printed cursive writing based on the DTW algorithm.

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

References

  1. 1.
    Abdennadher, N.: Vers un outil Peer-To-Peer orienté calcul intensif. In: Flash Informatique, EPFL, August 2005 Google Scholar
  2. 2.
    Abdennadher, N.: Using the volunteer computing platform XtremWeb-CH: lessons and perspectives. In: Workshop on Grid Computing: e-Infrastructure, Applications and Research, ESSTT, UTIC, Tunisia (2007) Google Scholar
  3. 3.
    Abdennadher, N.: XtremWeb-CH: une plateforme global computing pour les applications de haute performance. Internal report, August 2004, HES-SO/EIG Google Scholar
  4. 4.
    Al-Badr, A., Haralick, R.: A segmentation-free approach to text recognition with application to Arabic text. Int. J. Doc. Anal. Recognit. 1(3), 147–166 (1998) CrossRefGoogle Scholar
  5. 5.
    Alves, C.E.R., et al.: Parallel dynamic programming for solving the string editing problem on CGM/BSP. In: Proc. SPAA’02, Winnipeg, Manitoba, Canada, August 10–13, 2002 Google Scholar
  6. 6.
    Amin, A.: Off-line Arabic character recognition: the state of the art. Pattern Recognit. 31(5), 517–530 (1998) MathSciNetCrossRefGoogle Scholar
  7. 7.
    Available at http://www.nla.gov.au/
  8. 8.
  9. 9.
    Available at http://www.kirtas.com/
  10. 10.
  11. 11.
  12. 12.
  13. 13.
  14. 14.
    Bahi, J.M., et al.: Synchronous and asynchronous solution of a 3D transport model in a grid computing environment. Appl. Math. Model. 30, 616–628 (2006). Available on www.sciencedirect.com MATHCrossRefGoogle Scholar
  15. 15.
    Bertis, V., Bolze, R., Desprez, F., Reed, K.: Large scale execution of a bioinformatic application on a volunteer grid. In: IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2008, 14–18 April 2008, pp. 1–8 (2008) CrossRefGoogle Scholar
  16. 16.
    Bradford, P.G.: Efficient parallel dynamic programming. In: Proc. 30th Annual Allerton Conference on Communication, Control and Computing, University of Illinois, Urbana, IL, USA, pp. 185–194 (1992) Google Scholar
  17. 17.
    Bridle, J.S., et al.: An algorithm for connected word recognition. In: Proc. IEEE, ICASSP, pp. 899–902, May 1982 Google Scholar
  18. 18.
    Buyya, R., et al.: A gentle introduction to grid computing and technologies. In: Proc. CSI, India, May 7–19, 2005 Google Scholar
  19. 19.
    Capello, F.: The evolution of GRID5000. In: Workshop on Grid Computing: e-infrastructure, Applications and Research, ESSTT, UTIC Tunisia (2007) Google Scholar
  20. 20.
    Cheng, H.D., et al.: VLSI architecture for pattern matching using space-time domain expansion approach. In: Proc. IEEE Int. Conf. Computer Design VLSI Comput, NY, Oct 7–10, 1985 Google Scholar
  21. 21.
    Cheng, H.D., et al.: VLSI architecture for dynamic time-warp recognition of handwritten symbols. In: IEEE ASSP, vol. 34, Jan 1986 Google Scholar
  22. 22.
    Cheng, H.-D., et al.: A VLSI architecture for dynamic time-warp recognition of handwritten symbols. IEEE Trans. Acoust. Speech Signal Process. 34(3), 603–613 (1986) CrossRefGoogle Scholar
  23. 23.
    Cheung, A., et al.: An Arabic optical character recognition system using recognition based segmentation. Pattern Recognit. 34 (2001) Google Scholar
  24. 24.
    Coté, M., et al.: Une architecture Multi-agents réutilisables pour les environnements riches en informations. In: Série Scientifique, Montréal, July 2002 Google Scholar
  25. 25.
    Fedak, G., He, H., Cappello, F.: BitDew: a programmable environment for large-scale data, management and distribution. Technical report N 6427, INRIA, January 2008 Google Scholar
  26. 26.
    Ferber, J.: Les Systèmes Multi-agents. Vers une Intelligence Collective. InterEditios, Paris (1995) MATHGoogle Scholar
  27. 27.
    Foster, I., Kesselman, C., Tuecke, S.: The anatomy of the grid. Int. J. Supercomput. Appl. (2002) Google Scholar
  28. 28.
    Foster, I., Jennings, N.R., Kesselman, C.: Brain meets brawn: why grid and agents need each other. In: Proc. AAMAS’04, Leeds, UK, March 2004 Google Scholar
  29. 29.
    Gonzalez, R.C., Wintz, P.: BitDew: Digital Image Processing. Addison-Wesley, Reading (1988) Google Scholar
  30. 30.
    Hasegawa, W.: Research on Mobile Agent Security (510080). School of Information Science, Japan Advanced Institute of Science and Technology, February 2007 Google Scholar
  31. 31.
    Hayes, C.C.: Agents in a nutshell—a very brief introduction. IEEE Trans. Knowl. Data Eng. 11(1), 127–132 (1999) MathSciNetCrossRefGoogle Scholar
  32. 32.
  33. 33.
    IBM: Introduction to grid computing with Globus. IBM RedBook. SG24-6895-01. ISBN 0738427969, September 2003 Google Scholar
  34. 34.
    Jarras, I., Chaib-draa, B.: Aperçu sur les systèmes Multi-agents. In: Série Scientifique, Montréal, July 2002 Google Scholar
  35. 35.
    Jonquet, C.: Dynamic service generation: agent interactions for service exchange on the grid. Ph.D. dissertation, University of Montpellier II, November 2006 Google Scholar
  36. 36.
    Kanoun, S., et al.: Reconnaissance d’images de textes Arabes par approche Affixale. In: Proc. MCSEAI’04, Sousse, Tunisia, May 9–12, 2004 Google Scholar
  37. 37.
    Khemakhem, M.: Reconnaisance globale de caractères imprimés Arabes et Latins par comparaison dynamique. In: Proc. Regional Conference on Computer Science and Arabization, Tunis, Tunisia, March 1988 Google Scholar
  38. 38.
    Khemakhem, M., Belghith, A.: A multipurpose multi-agent system based on a loosely coupled architecture to speedup the DTW algorithm for Arabic printed cursive OCR. In: Proc. AICCSA-2005, Cairo, Egypt, January 2005 Google Scholar
  39. 39.
    Khemakhem, M., Belghith, A.: A P2P grid architecture for distributed Arabic OCR based on the DTW algorithm. Int. J. Comput. Appl. 31(1) (2009) Google Scholar
  40. 40.
    Khemakhem, M., et al.: Reconnaissance de caractères imprimés par comparaison dynamique. In: Proc. AFCET, Antibes, Sept. 1987 Google Scholar
  41. 41.
    Khemakhem, M., et al.: Arabic type written character recognition using dynamic comparison. In: Proc. 1st Computer Conference, Kuwait, March 1989 Google Scholar
  42. 42.
    Khemakhem, M., Belghith, A., Ben Ahmed, M.: Etude et evaluation de deux méthodes de distribution de l’algorithme de comparaison dynamique pour la reconnaissance de caractères Arabes. In: Proc. First Maghrebin Symposium on Programming and Systems, Algeria, October 1991 Google Scholar
  43. 43.
    Khemakhem, M., Belghith, A., Ben Ahmed, M.: Modélisation architecturale de la comparaison dynamique distribuée. In: Proc. Second International Congress on Arabic and Advanced Computer Technology, Casablanca, Morocco, December 1993 Google Scholar
  44. 44.
    Lesser, V.R.: Cooperative multi-agent systems: a personal view of the state of the art. IEEE Trans. Knowl. Data Eng. 11(1), 133–142 (1999) CrossRefGoogle Scholar
  45. 45.
    Mella, P.: Complex systems vs. Simplex systems: the behaviour of collectivities following the combinatory system view. In: Proc. 6th International Conference on Complex Systems (CS02), Complexity with Agent Based Modeling, Chuo University, Tokyo, Japan, September 9–11, 2002 Google Scholar
  46. 46.
    Quénot, G.R., et al.: A dynamic programming processor for speech recognition. IEEE J. Solid-State Circuits 24(F9), 20 (1989) Google Scholar
  47. 47.
    Russel, S., et al.: Artificial Intelligence: A Modern Approach. Prentice Hall, Englewood Cliffs (1995) Google Scholar
  48. 48.
    Shi, Z., et al.: Agent based grid computing. Appl. Math. Model. 30, 629–640 (2006). Available on www.sciencedirect.com MATHCrossRefGoogle Scholar
  49. 49.
    Vinciarelli, A.: A survey on off-line cursive word recognition. Pattern Recognit. 35, 1433–1446 (2002) MATHCrossRefGoogle Scholar
  50. 50.
    Weis, G.: Multi-agent Systems, a Modern Approach to Distributed Artificial Intelligence. MIT Press, Cambridge (1999) Google Scholar
  51. 51.
    Wolski, R.: Dynamically forecasting network performance using the network weather service. Ucsd Technical Report tr-cs96-494, University of California, San Diego, La Jolla, CA, January 7, 1998 Google Scholar
  52. 52.
    Wooldridge, M., et al.: Intelligent agents: theory and practice. Knowl. Eng. Rev. 10(2), 115–152 (1995) MathSciNetCrossRefGoogle Scholar
  53. 53.
    Wooldridge, M., et al.: A methodologie for agent oriented analysis and design. In: Proc. Third International Conference on Autonomous Agents (Agents’99), pp. 69–76. ACM, Seattle (1999) CrossRefGoogle Scholar
  54. 54.
    Worldlanguage products. Available at http://www.worldlanguage.com/ProductsArabic/OCR/Page1.htm

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  1. 1.MIRACL LabThe Higher Institute of Management University of SousseSousseTunisia
  2. 2.HANA Research Group, ENSIUniversity of ManoubaManoubaTunisia

Personalised recommendations