Isolated Arabic Characters Recognition Using a Robust Method Against Noise and Scaling Based on the «Hough Transform»

  • Mohammed Kadi Mohammed Premier University, Oujda, Morocco.
  • M’barek Nasri Mohammed Premier University, Oujda, Morocco.

Abstract

This work proposes a new approach based on the «Hough Transform» to feature extraction for isolated Arabic characters. The new approach supports multiple fonts and is resistant to noise, scaling, and translation. It is consists first in detecting loops and points in the structure of the entered Arabic character, and classifying it accordingly. Then the «Hough Transform» is used to detect the longest lines in the character structure, in different directions, and according to a well-chosen threshold. Afterwards, we have made improvements to this method, by introducing another threshold to consider also the shortest lines in the character structure. A recognition rate of 99% has been achieved for the recognition of Arabic characters written with fonts that have already been learned in the learning phase, and a remarkable rate for characters written with other fonts than those used in the learning phase. It was verified by many tests that the method is invariant by translation, that it is not too much affected by the noise and scaling.
Published
Jun 23, 2019
How to Cite
KADI, Mohammed; NASRI, M’barek. Isolated Arabic Characters Recognition Using a Robust Method Against Noise and Scaling Based on the «Hough Transform». International Journal of Information Science and Technology, [S.l.], v. 3, n. 4, p. 34 - 43, june 2019. ISSN 2550-5114. Available at: <http://innove.org/ijist/index.php/ijist/article/view/131>. Date accessed: 28 mar. 2024. doi: http://dx.doi.org/10.57675/IMIST.PRSM/ijist-v3i4.131.
Section
Special issue : Information and Multimedia Processing