Abstract
This paper proposes a new algorithm for Arabic optical font recognition (AOFR) as the first stage for Arabic optical character recognition. The proposed algorithm uses scale-invariant detector, gradient-based descriptor, and k-means clustering. The scale-invariant detector is used to find key points that identify the font of an image of printed Arabic text. The work in this paper compares between several scale-invariant detectors and selects the best one for AOFR. A gradient-based descriptor similar to the one in the famous scale-invariant feature transform algorithm is used to describe the detected key points. In addition, k-means clustering is used for font classification. In this paper, the mean recognition rate is used to evaluate the performance of the proposed algorithm. The proposed algorithm shows superior performance when compared with recently published algorithms for AOFR.
Similar content being viewed by others
References
Al-Badr, B., Mahmoud, S.A.: Survey and bibliography of Arabic optical text recognition. ELSEVIER Signal Process. 41, 49–77 (1995)
Slimane, F., Kanoun, S., Alimi, A.M., Ingold, R., Hennebert, J.: “Gaussian mixture models for Arabic font recognition”, In: Proceedings of international conference on pattern recognition, pp. 2174 – 2177, (2010)
Pourasad, Y., Ghorbani, A., ghouparanloo, S.: Farsi font and font size recognition based on analyzing binarization effect on small components of document images. J. Basic Appl., pp. 9563–9568 (2012)
Bataineh, B., Norul, S., Abdullah, H., Omar, K.: A statistical global feature extraction method for optical font recognition. In: Proceedings of the third international conference on intelligent information and database systems, Daegu, Korea, pp. 257–267, April 2011
Essoukri, N., Amara, B., Gazzah, S.: Une approche d’identification des fontes arabes. CIFED 8, 21–25 (2004)
Pourasad, Y., Hassibi, H., Ghorbani, A.: Farsi font recognition in document images using PPH features. Int. J. Nat. Eng. Sci. 5(3), 17–20 (2011)
Pourasad, Y., Hassibi, H., Ghorbani, A.: Farsi font recognition using holes of letters and horizontal projection profile, In: Proceedings of the first international conference on innovative computing technology, Tehran, Iran, pp. 235–243 (2011)
Slimane, F., Kanoun, S., Hennebert, J., Alimi, A.M., Ingold, Rolf: A study on font-family and font-size recognition applied to Arabic word images at ultra-low resolution. Pattern Recognit. Lett. 34, 209–218 (2013)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vis. 60(1), 63–86 (2004)
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Van Gool, L.: A comparison of affine region detectors. Springer Sci. Int. J. Comput. Vis. 65(1/2), 43–72 (2006)
Szeliski, R.: Computer Vision: Algorithms and Applications. Texts in Computer Sciences. Springer, London (2010)
Lowe, David G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 31–37 (2005)
Mackay, D.J.C.: Chapter 20. An example inference task: Clustering. In: Information theory, inference, and learning algorithms, Cambridge Univ. Press, Cambridge (2003)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mousa, M.A.A., Sayed, M.S. & Abdalla, M.I. An efficient algorithm for Arabic optical font recognition using scale-invariant detector. IJDAR 18, 263–270 (2015). https://doi.org/10.1007/s10032-015-0248-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-015-0248-9