CFP last date
22 April 2024
Reseach Article

Sequential Primitive Classifier Combination for Amazigh Alphabets OCR

by Mehdi Boutaounte, Youssef Ouadid
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 174 - Number 24
Year of Publication: 2021
Authors: Mehdi Boutaounte, Youssef Ouadid
10.5120/ijca2021921140

Mehdi Boutaounte, Youssef Ouadid . Sequential Primitive Classifier Combination for Amazigh Alphabets OCR. International Journal of Computer Applications. 174, 24 ( Mar 2021), 6-13. DOI=10.5120/ijca2021921140

@article{ 10.5120/ijca2021921140,
author = { Mehdi Boutaounte, Youssef Ouadid },
title = { Sequential Primitive Classifier Combination for Amazigh Alphabets OCR },
journal = { International Journal of Computer Applications },
issue_date = { Mar 2021 },
volume = { 174 },
number = { 24 },
month = { Mar },
year = { 2021 },
issn = { 0975-8887 },
pages = { 6-13 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume174/number24/31820-2021921140/ },
doi = { 10.5120/ijca2021921140 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:22:57.530440+05:30
%A Mehdi Boutaounte
%A Youssef Ouadid
%T Sequential Primitive Classifier Combination for Amazigh Alphabets OCR
%J International Journal of Computer Applications
%@ 0975-8887
%V 174
%N 24
%P 6-13
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The main difficulty in developing a successful Optical Character Recognition (OCR) system lies in the confusion between the characters. In the case of Amazigh writing (Tifinagh alphabets), some characters have similarities based on rotation or scale. Most of the researchers attempted to solve this problem by combining multiple descriptors and / or classifiers which increased the recognition rate, but at the expense of processing time that becomes more prohibitive. Thus, reducing the confusion of characters and their recognition times is the major challenge of OCR systems. In this paper, we present an off-line OCR system for Tifinagh characters. Using a proposed key point extraction algorithm, character skeleton is divided into several segments. The length and orientation of every segment are stored into a feature vector, then the relationship between these segments are represented by a graph in the form of an incidence matrix. Classification is done by searching for similarity between test images and their counterpart in the reference database by comparing their incidence matrix. When search provides multiple classes, feature victors are compared and input image is assigned to the closest class. Based on experiments done on 3300 images, an accuracy of 99% is achieved.

References
  1. Ait Ouguengay, Y., Taalabi, M., 2009a. Elaboration d’un réseau de neurones artificiels pour la reconnaissance optique de la graphie amazighe: Phase d’apprentissage. Systèmes Intell.-Théories Appl.
  2. Amrouch, M., Rachidi, A., El Yassa, M., Mammass, D., 2009. Printed amazigh character recognition by a hybrid approach based on Hidden Markov Models and the Hough transform, in: Multimedia Computing and Systems, 2009. ICMCS’09. International Conference On. IEEE, pp. 356–360.
  3. Amrouch, M., Es-Saady, Y., Rachidi, A., El-Yassa, M., Mammass, D., 2012. A novel feature set for recognition of printed amazigh text using maximum deviation and hmm. Int J Comput Appl 44.
  4. Ayachi, R.E., Fakir, M., Bouikhalene, B., 2011. Recognition of TIFINAGHE Characters Using A multilayer Neural Network. Int. J. Image Process. IJIP 5, 109.
  5. El Ayachi, R., Oujaoura, M., Fakir, M., Minaoui, B., 2014. Code Braille et la reconnaissance d’un document écrit en Tifinagh, in: Proceedings of the International Conference on Information and Communication Technologies for the Amazigh.
  6. Es Saady, Y., Rachidi, A., El Yassa, M., Mammas, D., 2010. Printed Amazigh Character Recognition by a Syntactic Approach using Finite Automata. Int. J. Graph. Vis. Image Process. 10, 1–8.
  7. Es Saady, Y., Rachidi, A., Elyassa, M., Mammass, D., 2008. Une méthode syntaxique pour la reconnaissance de caractères Amazighes imprimés. CARI’08.
  8. Bencharef, O., Fakir, M., Minaoui, B., Bouikhalene, B., 2011. Tifinagh Character Recognition Using Geodesic Distances, Decision Trees & Neural Networks. IJACSA Int. J. Adv. Comput. Sci. Appl. Spec. Issue Artif. Intell. 1–5.
  9. Oujaoura, M., El Ayachi, R., Minaoui, B., Fakir, M., Bouikhalene, B., Bencharef, O., 2013. Invariant descriptors and classifiers combination for recognition of isolated printed Tifinagh characters, in: Third International Symposium on Automatic Amazigh Processing (SITACAM’13). Beni-Mellal, Morocco.
  10. Oujaoura, Mustapha, Minaoui, B., Fakir, M., 2013. Walsh, Texture and GIST Descriptors with Bayesian Networks for Recognition of Tifinagh Characters. Int. J. Comput. Appl. 81.
  11. Ouadid, Youssef, Fakir, M., Minaoui, B., 2016. Tifinagh Printed Character Recognition through Structural Feature Extraction. Int. J. Comput. Vis. Image Process. IJCVIP 6, 42–53.
  12. Ouadid, Y., Minaoui, B., Fakir, M., 2016. Spectral Graph Matching for Printed Tifinagh Character, in: Computer Graphics, Imaging and Visualization (CGiV), 2016 13th International Conference On. IEEE, pp. 105–111.
  13. Ouadid, Y., Minaoui, B., Fakir, M., Abouelala, O., 2014. New Approach ofTifinagh Character Recognition using Graph Matching.
  14. Xu, X., Xu, S., Jin, L., Song, E., 2011. Characteristic analysis of Otsu threshold and its applications. Pattern Recognit. Lett. 32, 956–961.
  15. Zhang, T.Y., Suen, C.Y., 1984. A fast parallel algorithm for thinning digital patterns. Commun. ACM 27, 236–239.
  16. Djematen, A., Taconet, B., Zahour, A., 1998. Une méthode statistique pour la reconnaissance de caractères berbères manuscrits. CIFED ‘98 170–178.
  17. Oulamara, A., Duvernoy, J., 1988. An application of the Hough transform to automatic recognition of Berber characters. Signal Process. 14, 79–90.
Index Terms

Computer Science
Information Sciences

Keywords

Feature points Extraction Graph Theory Incidence Matrix