We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 November 2024
Reseach Article

A Novel Feature Set for Recognition of Printed Amazigh Text using Maximum Deviation and HMM

by M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, D. Mammass
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 44 - Number 12
Year of Publication: 2012
Authors: M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, D. Mammass
10.5120/6316-8659

M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, D. Mammass . A Novel Feature Set for Recognition of Printed Amazigh Text using Maximum Deviation and HMM. International Journal of Computer Applications. 44, 12 ( April 2012), 23-30. DOI=10.5120/6316-8659

@article{ 10.5120/6316-8659,
author = { M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, D. Mammass },
title = { A Novel Feature Set for Recognition of Printed Amazigh Text using Maximum Deviation and HMM },
journal = { International Journal of Computer Applications },
issue_date = { April 2012 },
volume = { 44 },
number = { 12 },
month = { April },
year = { 2012 },
issn = { 0975-8887 },
pages = { 23-30 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume44/number12/6316-8659/ },
doi = { 10.5120/6316-8659 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:35:21.982865+05:30
%A M. Amrouch
%A Y. Es-saady
%A A. Rachidi
%A M. El Yassa
%A D. Mammass
%T A Novel Feature Set for Recognition of Printed Amazigh Text using Maximum Deviation and HMM
%J International Journal of Computer Applications
%@ 0975-8887
%V 44
%N 12
%P 23-30
%D 2012
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The growing need of Tifinagh characters recognition in several domains in Morocco such as education, telecommunication, etc, has made it a vital area of research. This paper presents a novel set of structural features generated on the Tifinagh character geometry. This set based on a vocabulary that consists of various fundamental strokes, which is generated using the intrinsic morphological characteristics of the Amazigh script. The input text image is undergoing several preprocessing operations: binarization, skew correction, line segmentation, character segmentation and size normalization. Indeed, the obtained isolated characters are first pre-classified into one of two character groups (circular, non-circular) using the Hough Transformation method. Then, each one is described with their points that have maximum deviation and their segments. Thereafter, each segment of the character is transformed into primitives sequence. We use the discriminating path (DP-HMM) recognition system witch operates on proposed vocabulary. Only one model is built and trained on all elements of this vocabulary. Each path through this trellis represents a sequence of segments, i. e. the character of the Tifinagh alphabet. Finally, the recognition is performed by dynamically decoding the optimal path according to the criterion of maximum likelihood. The obtained scores show the robustness of the proposed approach

References
  1. Herman Ney and Stephan Ortmanns, Progress in dynamic programming search for LVCSR. Proceedings of the IEEE, 88(8), pp. 1224–1240, August 2000.
  2. Xuedong Huang, Alex Acero, and Hsiao-Wuen Hon, Spoken language processing, Prentice Hall, 2001.
  3. Nafiz Arica and Fatos T. Yarman-Vural, An overview of character recognition focused on off-line handwriting, IEEE Transactions on Systems, Man and Cybernetics - part C: Applications and Reviews, 31(2), pp. 216–233, May 2001.
  4. A. Benouareth Reconnaissance de Mots Arabes Manuscrits par Modèles de Markov Cachés à Durée d'Etat Explicite PhD thesis, Univ Badji Mokhtar, Annaba V, 2007.
  5. X. Dupre, Contributions à la reconnaissance de l'écriture cursive `a l'aide de modèles de Markov caches, PhD thesis, Univ Rene Descartes, Paris V, 2003.
  6. F. Menasri, Contributions à la reconnaissance de l'écriture arabe manuscrite, PhD thesis, Université Descartes, Paris, 2008.
  7. Y. Es-Saady, Contribution au développement d'approches de reconnaissance automatique de caractères imprimés et manuscrits, de textes et de documents amazighes, PhD thesis, Université Ibn zohr, Agadir, 2012.
  8. M. Amrouch, Y. Es saady, A. Rachidi, M. Elyassa, D. Mammass, Printed Amazigh Character Recognition by a Hybrid Approach Based on Hidden Markov Models and the Hough Transform, ICMCS'09, Avril 2009, Ouarzazate, Maroc.
  9. M. Amrouch, M. Elyassa, A. Rachidi, D. Mammass, Handwritten Amazigh Character Recognition Based on Hidden Markov Models, ICGST-GVIP Journal, Vol. 10, Issue 5, pp. 11-18, 2010.
  10. M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, D. Mammass, Handwritten Amazigh Character Recognition System Based on Continuous HMMs and Directional Features, International Journal of Modern Engineering Research (IJMER), Vol. 2, Issue. 2, pp-436-441, Mar-Apr 2012.
  11. A. Ait Ouguengay, Elaboration d'un réseau de neurones artificiel pour la reconnaissance optique de la graphie amazighe, Phase d'apprentissage, SITA'08, 5ème conférence sur les systèmes intelligents : Théories et applications, INPT, Mai 2008, Rabat-Maroc.
  12. N. Otsu. A threshold selection method from grey-level histograms, IEEE Trans. Syst. Man. Cybern. , vol. SMC-8, 1978.
  13. H. Yan, "Skew correction of document images using interline cross-correlation", CVGIP: Graphical Models Image Process 55, 1993, 538-543.
  14. T. Pavlidis and J. Zhou, Page segmentation and Classification, Comput. Vision Graphics Image Process. 54, 1992, 484-496.
  15. D. S. Le, G. R. Thoma and H. Wechsler, Automatic page orientation and skew angle detection for binary document images, Pattern Recognition 27, 1994, 1325-1344.
  16. Y. Es Saady, A. Rachidi, M. El Yassa, D. Mammass, Amazigh Handwritten Character Recognition based on Horizontal and Vertical Centerline of Character, International Journal of Advanced Science and Technology, vol. 33, pp. 33-50, August, 2011.
  17. S. N. Srihari, E. J. Keubert. Integration of handwritten address interpretation technology into the United States postal service remote computer reader system, ICDAR, pages 892–896, 1997.
  18. Henri Maitre, Un panorama de la transformation de Hough, École Nationale Supérieure des Télécommunications, Labo Image, Département Images, Sons et Vidéo, traitement de sgnal, vol. 2, n. 4, 1985.
  19. Grandidier F. , Sabourin R. , Suen C. Y. , and Gilloux M. , Une nouvelle stratégie pour l'amélioration des jeux de primitives d'un système de reconnaissance de l'écriture, CIFED'2000, pp. 111-120, July 2000, Lyon, France.
  20. Britto, A. S. , Sabourin R. , Bortolozzi F. and Suen C. Y. , "Foreground and Background Information in an HMM-Based Method for Recognition of Isolated Characters and Numeral Strings", 9th IWFHR, pp 371-376, October, 2004, Tokyo, Japan.
  21. M. K. Hu, Pattern recognition by moment invariants, In Proc. IRE, pp. 1428, Sept. 1961.
  22. Perter Kovesi, Invariant Mesures of Image Features from phase Information, rapport thèse, département de psychologie, université de Western Australia, May 1996.
  23. L. R. Rabiner. A Tutorial on Hidden Markov Modelsand Selected Applications in Speech Recognition. Proceedings of the IEEE, vol. 77, no. 2, pages 257–286, 1989.
  24. Rabiner, L. , and Juang, B. Fundamentals of speech recognition, Prentice Hall, 1993.
  25. E. Augustin, Reconnaissance de mots manuscrits par systèmes hybrides Réseaux de Neurones et Modèles de Markov Cachés, PhD thesis, Paris, 2001.
  26. M. Amrouch,Y. Es-Saady, A. Rachidi, M. El Yassa, D. Mammass, A New Approach Based On Strokes for Printed Tifinagh Characters Recognition Using the Discriminating Path-HMM, accepted by IRECOS Journal, in press, march 2012.
  27. Y. Es Saady, Ali Rachidi, Mostafa El Yassa and Driss Mammass, AMHCD: A Database for Amazigh Handwritten Character Recognition Research. International Journal of Computer Applications 27(4):44-49, New York, USA August 2011.
Index Terms

Computer Science
Information Sciences

Keywords

Tifinagh Characters Recognition Structural Features Dp-hmms Dynamic Programming Maximum Deviation