Abstract
The main problem in the handwritten character recognition systems (HCR) is to describe each character by a set of features that can distinguish it from the other characters. Thus, in this paper, we propose a robust set of features extracted from isolated Amazigh characters based on decomposing the character image into zones and calculate the density and the total length of the histogram projection in each zone. In the experimental evaluation, we test the proposed set of features, to show its performance, with different classification algorithms on a large database of handwritten Amazigh characters. The obtained results give recognition rates that reach 99.03% which we presume good and satisfactory compared to other approaches and show that our proposed set of features is useful to describe the Amazigh characters.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
H. Mirvaziri, M. Masood Javidi, and N. Mansouri, “Handwriting recognition algorithm in different languages: survey,” Int. Lecture Notes Comput. Sci. 5857, 487–497 (2009).
Y. Elarian, R. Abdel-Aal, I. Ahmad, M. Parvez, and A. Zidouri, “Handwriting synthesis: classifications and techniques,” Int. J. Document Anal. Recogn. 17 (4), 455–469 (2014).
N. Tagougui, M. Kherallah, and M. Alimi, “Online arabic handwriting recognition: a survey,” Int. J. Document Anal. Recogn. 16 (3), 209–226 (2013).
S. Bag and G. Harit, “A survey on optical character recognition for Bangla and Devanagari script,” Sadhana 38 (1), 133–168 (2013).
M. Ameur, A. Bouhjar, F. Boukhris, A. Boukouss, A. Boumalk, M. Elmedlaoui, E. Iazzi, and H. Souifi, “Initiation à la langue amazighe,” Publications de l’Institut Royal de la Culture Amazighe, Manuels, No. 1, 9 (2004).
Presentation of The Royal Institute of the Amazigh Culture (2014). http://www.ircam.ma/doc/divers/presentation_ of_ircam.pdf.
A. Oulamara and J. Duvernoy, “An application of the hough transform to automatic recognition of Berber characters,” Signal Processing 14 (1), 79–90 (1988).
A. Djematene, B.Taconet, and A. Zahour, “A geometrical method for printing and handwritten Berber characters recognition,” in Proc. 4th Int. Conf. on Document Analysis and Recognition (Ulm, 1997), Vol. 2, pp. 564–567.
M. Amrouch, A. Rachidi, M. El Yassa, and D. Mammass, “Handwritten amazigh character recognition based on hidden Markov models,” J. Graph., Vision Image Processing 10 (5), 11–18 (2010).
M. Amrouch, Y. Es-saady, A. Rachidi, M. El Yassa, and D. Mammass, “Handwritten amazigh character recognition system based on continuous HMMs and directional features,” Int. J. Modern Eng. Res. 2 (2), 436–441 (2012).
Y. Es Saady, A. Rachidi, M. El Yassa, and D. Mammass, “Amazigh handwritten character recognition based on horizontal and vertical centerline of character,” Int. J. Adv. Sci. Technol. 33, 33–50 (2011).
M. Abaynarh, H. Elfadili, and L. Zenkouar, “Recognition of Tifinaghe handwritten characters using moments for feature extraction,” in Proc. 4th atelier international sur l’amazighe et les TICs: Les resources langagieres: construction et exploitation (2011), pp. 345–356.
M. Abaynarh, H. Elfadili, and L. Zenkouar, “Enhanced feature extraction of handwritten characters and recognition using artificial neural networks,” J. Theor. Appl. Inf. Technol. 72 (3), 355–365 (2015).
S. Gounane, M. Fakir, and B. Bouikhalene, “Handwritten Tifinagh text recognition using fuzzy K-NN and Bi-gram language model,” in Selected Papers from 3rd Int. Symp. on Automatic Amazigh Processing (SITACAM’ 13) (Beni Mellal, 2013), Special Issue, pp. 29–32.
H. Moudni, M. Er-rouidi, M. Oujaoura, and O. Bencharef, “Recognition of amazigh characters using SURF & GIST descriptors,” Int. J. Adv. Comput. Sci. Appl. Special Issue on Selected Papers from 3rd Int. Symp. on Automatic Amazigh Processing (2013), pp. 41–44.
N. Chaki, S. Shaikh, and K. Saeed, “A comprehensive survey on image binarization techniques,” Studies Comput. Intellig. 560, 5–15 (2014).
N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979).
B. Jain and M. Borah, “Simple and effective techniques for skew correction, slant correction and core-region detection for cursive word recognition,” Adv. Intellig. Soft Comput. 132, 353–361 (2012).
T. Saba, A. Rehman, and M. Elarbi-Boudihir, “Methods and strategies on off-line cursive touched characters segmentation: a directional review,” Artif. Intellig. Rev. 42 (4), 1047–1066 (2014).
A. Muñoz Barrutia, T. Blu, and M. Unser, “Leastsquares image resizing using finite differences,” IEEE Trans. Image Processing 10 (9), 1365–1378 (2001).
N. Arica and F. T. Yarman-Vural, “An overview of character recognition focused on off-line handwriting,” IEEE Trans. Syst. Man Cybern. C Appl. 31 (2), 216–232 (2001).
A. F. R. Rahman, H. Alam, and M. C. Fairhurst, “Multiple classifier combination for character recognition: revisiting the majority voting system and its variations,” Lecture Notes Comput. Sci. 2423, 167–178 (2002).
Y. Es Saady, A. Rachidi, M. El Yassa, and D. Mammass, “AMHCD: a database for amazigh handwritten character recognition research,” Int. J. Comput. Appl. 27 (4), 44–48 (2011).
M. Sokolova, N. Japkowicz, and S. Szpakowicz, “Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation,” Lecture Notes Comput. Sci. 4304, 1015–1021 (2006).
C. Chow, “On optimum recognition error and reject tradeoff,” IEEE Trans. Inf. Theory 16 (1), 41–46 (1970).
G. Fumera, F. Roli, and G. Giacinto, “Multiple reject thresholds for improving classification reliability,” Lecture Notes Comput. Sci. 1876, 863–871 (2000).
H. Cecotti and S. Vajda, “Rejection schemes in multiclass classification–application to handwritten character recognition,” in Proc. 12th Int. Conf. on Document Analysis and Recognition (Washington, 2013), pp. 445–449.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Nabil AHARRANE received his MSc degree in computer science and imaging in 2008 from USMBA University in Morocco. Now he is a PhD student at the Department of computer science at the same University on the subject of Pattern recognition. His interests include OCR Systems problems, machine learning and features extraction from images.
Karim EL MOUTAOUAKIL received the PhD degree from the Faculty of sciences and technologies in Fez-Morocco in 2011. He is currently an Assistant professor of computer science at the National school of applied sciences in Al-Hoceima- Morocco. His research interests include Articiciel intelligence, machine larnining and pattern recognition.
Abdellatif DAHMOUNI received his MSc degree in computer science and imaging in 2013 from USMBA University in Morocco. Now he is a PhD student at the Department of computer science at the same University on the subject of Pattern recognition. His interests include face recognition problems, machine learning and Local Binary Pattern.
Khalid SATORI received the PhD degree from the National Institute for the Applied Sciences INSA at Lyon in 1993. He is currently a full professor of computer science at USMBA University in Morocco. His is the director of the LIIAN Laboratory. His research interests include real-time rendering, Imagebased rendering, virtual reality, biomedical signal, camera self calibration and 3D reconstruction and pattern recognition.
Rights and permissions
About this article
Cite this article
Aharrane, N., Dahmouni, A., El Moutaouakil, K. et al. A robust statistical set of features for Amazigh handwritten characters. Pattern Recognit. Image Anal. 27, 41–52 (2017). https://doi.org/10.1134/S1054661817010011
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661817010011