JACIII Vol.10 No.1 pp. 17-25
doi: 10.20965/jaciii.2006.p0017


A Hybrid Neuro-Symbolic Approach for Arabic Handwritten Word Recognition

Labiba Souici-Meslati, and Mokhtar Sellami

Department of Informatics, LRI Laboratory, Badji Mokhtar University, BP 12, 23000, Annaba, Algeria

October 27, 2003
October 5, 2005
January 20, 2006
holistic recognition of arabic handwritten words, neuro-symbolic combination, knowledge based neural networks

In this article, we suggest a system that automatically constructs knowledge based artificial neural networks (KBANN) for the holistic recognition of handwritten Arabic words in limited lexicons. To build a neuro-symbolic KBANN classifier for a given vocabulary, ideal samples of its words are first submitted to a structural feature extraction module. The analysis of the presence and possible occurrence numbers for these features in the considered lexicon enables to generate a symbolic knowledge base reflecting a hierarchical classification of the words. A rules-to-network translation algorithm uses this knowledge to build a multilayer neural network. It determines precisely its architecture and initializes its connections with specific values rather than random values, as is the case in classical neural networks. This construction approach provides the network with theoretical knowledge and reduces the training stage, which remains necessary because of styles and writing conditions variability. After this empirical training stage using real examples, the network acquires a final topology, which allows it to recognize new handwritten words. The proposed method has been tested on the automated construction of neuro-symbolic classifiers for two Arabic lexicons: literal amounts and city names. The application of this approach to the recognition of handwritten words or characters in different scripts and languages is also considered.

Cite this article as:
Labiba Souici-Meslati and Mokhtar Sellami, “A Hybrid Neuro-Symbolic Approach for Arabic Handwritten Word Recognition,” J. Adv. Comput. Intell. Intell. Inform., Vol.10, No.1, pp. 17-25, 2006.
Data files:
  1. [1] B. Al. Badr, and S. A. Mahmoud, “Survey and bibliography of Arabic optical text recognition,” Signal processing, Vol.41, pp. 49-77, 1995.
  2. [2] A. Amin, “Off-line arabic character recognition: The state of the art,” Pattern Recognition, Vol.31, No.5, pp. 517-530, 1998.
  3. [3] H. Bunke, “Recognition of Cursive Roman Handwriting – Past, Present and Future,” International Conference on Document Analysis and Recognition, ICDAR, Edinburgh, Scotland, 2003.
  4. [4] D. Cakmakov, and Y. Bennani, “Feature selection for pattern recognition,” Skopje, Informa, 2002.
  5. [5] N. Essoukhri Ben Amara, and F. Bouslama, “Classification of Arabic script using multiple sources of information: state of the art and perspectives,” International Journal on Document Analysis and Recognition, IJDAR, Vol.5, pp. 195-212, 2003.
  6. [6] N. Farah, L. Souici, L. Farah, and M. Sellami, “Arabic words recognition with classifier combination: An application to literal amounts,” Lecture Notes in Artificial Intelligence, LNAI 3192, pp. 420-429, Springer, 2004.
  7. [7] S. Madhvanath, and V. Govindaraju, “Perceptual features for offline handwritten word recognition: a framework for heuristic prediction, representation and matching,” Lecture Notes in Computer Science, LNCS 1451, pp. 524-531, 1998.
  8. [8] S. Madhvanath, and V. Govindaraju, “The role of holistic paradigms in handwritten word recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.23, No.2, pp. 149-164, 2001.
  9. [9] S. A. Mahmoud, “Arabic character recognition using Fourier descriptors and character contour encoding,” Pattern Recognition, Vol.27, No.6, pp. 815-824, 1994.
  10. [10] K. McGarry, S. Wermter, and J. MacIntyre, “Hybrid neural systems: from simple coupling to fully integrated neural networks,” Neural Computing Surveys, Vol.2, pp. 62-94, 1999.
  11. [11] T. Pavlidis, “Algorithms for Graphic and Image Processing,” Rockville, MD: Computer science press, 1982.
  12. [12] L. Schomaker, and E. Segers, “Finding features used in the human reading of cursive handwriting,” International Journal on Document Analysis and Recognition, IJDAR, Vol.2, No.1, pp. 13-18, 1999.
  13. [13] L. Souici, A. Aoun, and M. Sellami, “Global recognition system for Arabic literal amounts,” International Conference on Computer Technologies and Applications, ICCTA’99, Alexandria, Egypt, 1999.
  14. [14] L. Souici-Meslati, and M. Sellami, “Reconnaissance des montants littéraux arabes par un système hybride neuro-symbolique,” RFIA 2002, 11th Congrès francophone AFRIF-AFIA de Reconnaissance des Formes et Intelligence Artificielle, pp. 917-926, Angers, France, 2002.
  15. [15] L. Souici, N. Farah, T. Sari, and M. Sellami, “Rule based neural networks construction for handwritten arabic city-names recognition,” Lecture Notes in Artificial Intelligence, LNAI 3192, pp. 331-340, Springer, 2004.
  16. [16] T. Steinherz, E. Rivlin, and N. Intrator, “Offline cursive script recognition: a survey,” IJDAR, International Journal on Document Analysis and Recognition, Vol.2, pp. 90-110, 1999.
  17. [17] C. Suen, S. Mori, S. Kim, and C. Leung, “Analysis and Recognition of Asian Scripts – The State of the Art,” International Conference on Document Analysis and Recognition, ICDAR, Edinburgh, Scotland, 2003.
  18. [18] G. G. Towell, “Symbolic knowledge and neural networks: insertion, refinement and extraction,” PhD thesis, University of Wisconsin, Madison, WI, 1991.
  19. [19] G. G. Towell, and J. W. Shavlic, “Knowledge-based artificial neural networks,” Artificial Intelligence, Vol.70, pp. 119-165, 1994.
  20. [20] A. Vinciarelli, “A survey on off-line Cursive Word Recognition,” Pattern Recognition, Vol.35, pp. 1433-1446, 2002.
  21. [21] S. Wermter, and R. Sun, “Hybrid neural systems,” Springer, 2000.

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

Last updated on Mar. 01, 2021