| Peer-Reviewed

Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning

Received: 6 July 2022     Accepted: 20 July 2022     Published: 28 July 2022
Views:       Downloads:
Abstract

Deep convolutional neural networks are one of the most promising techniques to recognize objects, letters and digits. The recognition of handwritten digits is of great importance in many applications such as digits as password on cell phones, simplifying teaching children numbering systems. The Arabic handwritten digits recognition (AHDR) is an example of using deep learning in recognizing Arabic handwritten digits. The Arabic digits systems or Hindu digits are difficult to process using object recognition due to the similarities of digits to each other, which is totally different from the most popular English language digits as the English numbers are more variant than Arabic numbering systems. The Deep convolutional neural networks techniques have many different layers properties which depends on number of neurons, filter dimensions and strides which are called hyperparameters to achieve higher performance in recognizing the Eastern Arabic digits more than other techniques. The Eastern Arabic digits system has some varieties than other number systems which makes the recognition of handwritten digits are more challenging than other numbering systems. In this paper, multi hidden layers using deep convolutional networks will be applied to Arabic handwritten digits recognition. This technique outperforms other techniques with respect to minimum cost function and maximum accuracy compared to other techniques.

Published in American Journal of Science, Engineering and Technology (Volume 7, Issue 3)
DOI 10.11648/j.ajset.20220703.11
Page(s) 57-61
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Deep Learning, Convolutional Networks, Machine Learning, Object

References
[1] M. A. Nielsen, Neural networks and deep learning, vol. 2018. Determination press San Francisco, CA, 2015.
[2] O. I. Abiodun et al., “Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition,” IEEE Access, vol. 7, no. February 2017, pp. 158820–158846, 2019, doi: 10.1109/ACCESS.2019.2945545.
[3] M. Ramzan et al., “A survey on using neural network based algorithms for hand written digit recognition,” International Journal of Advanced Computer Science and Applications, vol. 9, no. 9, pp. 519–528, 2018, doi: 10.14569/ijacsa.2018.090965.
[4] C. Arndt, Information Measures Information and its Description in Science and Engineering. 2001.
[5] G. Ifrah, The universal history of computing. John Wiley & Sons, Inc., 2000.
[6] O. ELMelhaoui, M. ELHitmy, and F. Lekhal, “Arabic Numerals Recognition based on an Improved Version of the Loci Characteristic,” International Journal of Computer Applications, vol. 24, no. 1, pp. 36–41, 2011, doi: 10.5120/2912-3830.
[7] H. A. Morsy, “Optimization of Arabic Handwritten digits recognition using CNN,” International Journal of Scientific & Engineering Research V, vol. 11, no. 11, pp. 372–376, 2020.
[8] H. A. Morsy, “Developing a New CCN Technique for Arabic Handwritten Digits Recognition,” International Journal of Recent Technology and Engineering (IJRTE), vol. 9, no. 3, pp. 520–524, 2020, doi: 10.35940/ijrte.C4588.099320.
[9] D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, pp. 1–15, 2015.
[10] R. M. Gray, Entropy and information theory. 2011. doi: 10.1007/978-1-4419-7970-4.
[11] Y. Lecun, L. Bottou, Y. Bengio, and P. Ha, “Gradient-Based Learning Applied to Document,” Proceedings of the IEEE, no. November, pp. 1–46, 1998, doi: 10.1109/5.726791.
[12] P. Selvi and T. Meyyappan, “Recognition of Arabic numerals with grouping and ungrouping using back propagation neural network,” in Pattern Recognition, Informatics and Mobile Engineering (PRIME), 2013, p. 322—327. doi: 10.1109/ICPRIME.2013.6496494.
[13] S. Mahmoud, “Arabic (Indian) handwritten digits recognition using Gabor-based features,” in Innovations in Information Technology, 2008. IIT 2008. 2008, p. 683—687. doi: 10.1109/INNOVATIONS.2008.4781779.
[14] M. Takruri, R. ALHmouz, and A. ALHmouz, “A three-level classifier: fuzzy C means, support vector machine and unique pixels for Arabic handwritten digits,” in World Symposium on Proceedings of Computer Applications & Research (WSCAR), 2014, p. 1—5. doi: 10.1109/WSCAR.2014.6916798.
[15] J. H. Alkhateeb and M. Alseid, “DBN - Based learning for Arabic handwritten digit recognition using DCT features,” 2014 6th International Conference on Computer Science and Information Technology, CSIT 2014 - Proceedings, no. September, pp. 222–226, 2014, doi: 10.1109/CSIT.2014.6806004.
[16] J.-C. Vialatte, V. Gripon, and G. Coppin, “Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs,” Jun. 2017.
[17] A. ELSawy, H. ELBakry, and M. Loey, “CNN for Handwritten Arabic Digits Recognition Based on LeNet-5,” in Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2017, pp. 566–575. doi: 10.1007/978-3-319-48308-5_54.
[18] M. Salameh, “Arabic digits recognition using statistical analysis for end/conjunction points and fuzzy logic for pattern recognition techniques,” World Comput. Sci. Inf. Technol. J, vol. 4, no. 4, pp. 50–56, 2014.
[19] A. ELSawy, H. ELBakry, and M. Loey, “CNN for Handwritten Arabic Digits Recognition Based on LeNet-5,” 2017. doi: 10.1007/978-3-319-48308-5.
Cite This Article
  • APA Style

    Hamdy Amin Morsy. (2022). Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning. American Journal of Science, Engineering and Technology, 7(3), 57-61. https://doi.org/10.11648/j.ajset.20220703.11

    Copy | Download

    ACS Style

    Hamdy Amin Morsy. Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning. Am. J. Sci. Eng. Technol. 2022, 7(3), 57-61. doi: 10.11648/j.ajset.20220703.11

    Copy | Download

    AMA Style

    Hamdy Amin Morsy. Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning. Am J Sci Eng Technol. 2022;7(3):57-61. doi: 10.11648/j.ajset.20220703.11

    Copy | Download

  • @article{10.11648/j.ajset.20220703.11,
      author = {Hamdy Amin Morsy},
      title = {Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning},
      journal = {American Journal of Science, Engineering and Technology},
      volume = {7},
      number = {3},
      pages = {57-61},
      doi = {10.11648/j.ajset.20220703.11},
      url = {https://doi.org/10.11648/j.ajset.20220703.11},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajset.20220703.11},
      abstract = {Deep convolutional neural networks are one of the most promising techniques to recognize objects, letters and digits. The recognition of handwritten digits is of great importance in many applications such as digits as password on cell phones, simplifying teaching children numbering systems. The Arabic handwritten digits recognition (AHDR) is an example of using deep learning in recognizing Arabic handwritten digits. The Arabic digits systems or Hindu digits are difficult to process using object recognition due to the similarities of digits to each other, which is totally different from the most popular English language digits as the English numbers are more variant than Arabic numbering systems. The Deep convolutional neural networks techniques have many different layers properties which depends on number of neurons, filter dimensions and strides which are called hyperparameters to achieve higher performance in recognizing the Eastern Arabic digits more than other techniques. The Eastern Arabic digits system has some varieties than other number systems which makes the recognition of handwritten digits are more challenging than other numbering systems. In this paper, multi hidden layers using deep convolutional networks will be applied to Arabic handwritten digits recognition. This technique outperforms other techniques with respect to minimum cost function and maximum accuracy compared to other techniques.},
     year = {2022}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Performance Analyses of the Eastern Arabic Hand Written Digits Recognition Using Deep Learning
    AU  - Hamdy Amin Morsy
    Y1  - 2022/07/28
    PY  - 2022
    N1  - https://doi.org/10.11648/j.ajset.20220703.11
    DO  - 10.11648/j.ajset.20220703.11
    T2  - American Journal of Science, Engineering and Technology
    JF  - American Journal of Science, Engineering and Technology
    JO  - American Journal of Science, Engineering and Technology
    SP  - 57
    EP  - 61
    PB  - Science Publishing Group
    SN  - 2578-8353
    UR  - https://doi.org/10.11648/j.ajset.20220703.11
    AB  - Deep convolutional neural networks are one of the most promising techniques to recognize objects, letters and digits. The recognition of handwritten digits is of great importance in many applications such as digits as password on cell phones, simplifying teaching children numbering systems. The Arabic handwritten digits recognition (AHDR) is an example of using deep learning in recognizing Arabic handwritten digits. The Arabic digits systems or Hindu digits are difficult to process using object recognition due to the similarities of digits to each other, which is totally different from the most popular English language digits as the English numbers are more variant than Arabic numbering systems. The Deep convolutional neural networks techniques have many different layers properties which depends on number of neurons, filter dimensions and strides which are called hyperparameters to achieve higher performance in recognizing the Eastern Arabic digits more than other techniques. The Eastern Arabic digits system has some varieties than other number systems which makes the recognition of handwritten digits are more challenging than other numbering systems. In this paper, multi hidden layers using deep convolutional networks will be applied to Arabic handwritten digits recognition. This technique outperforms other techniques with respect to minimum cost function and maximum accuracy compared to other techniques.
    VL  - 7
    IS  - 3
    ER  - 

    Copy | Download

Author Information
  • Electronics and Communications Engineering Department, Faculty of Engineering, Helwan University, Cairo, Egypt

  • Sections