Writer Identification Using Modular MLP Classifier and Genetic Algorithm for Optimal Features Selection

  • Sami Gazzah
  • Najoua Essoukri Ben Amara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)


This paper describes the design and implementation of a system that identify the writer using off-line Arabic handwriting. Our approach is based on the combination of global and structural features. We used genetic algorithm for feature subset selection in order to eliminate the redundant and irrelevant ones. A modular Multilayer Perceptron (MLP) classifier was used. Experiments have shown writer identification accuracies reach acceptable performance levels with an average rate of 94.73% using optimal feature subset. Experiments are carried on a database of 180 text samples, whose text was made to ensure the involvement of the various internal shapes and letters locations within a word.


Genetic Algorithm Feature Subset Optimal Subset Feature Subset Selection Optimal Feature Subset 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Srihari, S.N., Cha, S.H., Arora, H., Lee, S.: Individuality of Handwriting. Journal of Forensic Sciences 47(4), 856–872 (2002)Google Scholar
  2. Cha, S.H., Srihari, S.H.: Multiple Feature Integration for Writer Verification. In: Proceeding of the 7th International Workshop on Frontiers in Handwriting Recognition (IWFHR 2000), Amsterdam, September 2000, pp. 333–342 (2000)Google Scholar
  3. Writer Identification Using Arabic Script. The second International Conference on Machine Intelligence (ACIDCA-ICMI 2005), Tozeur/Tunisia, 1001-1005 (2005)Google Scholar
  4. Korsheed, M.S.M.: Automatic Recognition of words in Arabic manuscripts. PhD thesis, Churchill College University Of Cambridge (2000)Google Scholar
  5. Amara, N., Ellouze, N.: Overview and Advances in Arabic Optical Character Recognition. Asian Journal on Information Technology, Grace Publications Network 3, 217–240 (2004)Google Scholar
  6. Raymer, M., Punch, W.F., Goodman, E.D., Kuhn, L.A., Jain, A.K.: Dimensionality Reduc-tion Using Genetic Algorithms. IEEE Transactions on Evol. Comput. 4, 164–171 (2000)CrossRefGoogle Scholar
  7. Oliveira, L.S.: A Methodology for Feature Selection Using Multi-objective Genetic Algorithms for Handwritten Digit String. International Journal of Pattern Recognition and Artificial intelligence 17(6), 903–929 (2003)CrossRefGoogle Scholar
  8. John, G.H., Kohavi, R., Pfleger, K.: Irrelevant Feature and the Subset Selection Problem. In: Eleventh International Conference on Machine learning (ML 1994), New Brunswick (1994)Google Scholar
  9. Gazzah, S., Amara, N.: Utilisation des Ondelettes et des Réseaux de Neurones en Identification des Fontes Arabes. In: Conférence Internationale Signaux, Circuits et Systèmes (SCS 2004), Monastir/Tunisia, pp. 498–502 (2004)Google Scholar
  10. Gazzah, S., Amara, N.: Writer Identification Using SVM Classifier and Genetic Algorithm for Optimal Futures Selection. In: International Arab Conference on Information Technology (ACIT 2005), Amman / Jordan, pp. 461–466 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sami Gazzah
    • 1
  • Najoua Essoukri Ben Amara
    • 2
  1. 1.Laboratoire des Systèmes et du Traitement de Signal (LSTS)Ecole National d’Ingénieurs de Tunis (ENIT) 
  2. 2.Ecole Nationale d’ingénieurs de Sousse 4000SousseTunisie

Personalised recommendations