DOI QR코드

DOI QR Code

Arabic Text Recognition with Harakat Using Deep Learning

  • Ashwag, Maghraby (Umm Al-Qura University, College of Computer and Information Systems) ;
  • Esraa, Samkari (Umm Al-Qura University, College of Computer and Information Systems)
  • Received : 2023.01.05
  • Published : 2023.01.30

Abstract

Because of the significant role that harakat plays in Arabic text, this paper used deep learning to extract Arabic text with its harakat from an image. Convolutional neural networks and recurrent neural network algorithms were applied to the dataset, which contained 110 images, each representing one word. The results showed the ability to extract some letters with harakat.

Keywords

References

  1. Mohd, M., Qamar, F., Al-Sheik, I., Salah, R.: Quranic optical text recognition using deep learning models. In: IEEE Access, vol. 99, pp. 1, 2011.
  2. Fasha, M., Hammo, B., Obeid, N.: A hybrid deep learning model for Arabic text recognition. In: International Journal of Advanced Computer Science and Applications (IJACSA), vol.11(8), 2020.
  3. Ranjan, J., Amrita, C., Sk, I.: Optical character recognition from text imagel. In: International Journal of Computer Applications Technology and Research, vol.3(4), pp.240-244, 2014. https://doi.org/10.7753/IJCATR0304.1009
  4. Anwar, K., Nugroho, H.: A segmentation scheme of Arabic words with harakat In: 2015 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), pp. 111-114, (2015)
  5. Qaroush, A., Awad, A., Modallal, M., Ziq, M.: Segmentation-based omnifont printed Arabic character recognition without font identification. In: Journal of King Saud University - Computer and Information Sciences, (2020)
  6. Ryding, K.: A reference grammar of modern standard Arabic. In: Cambridge, UK: Cambridge University Press, pp. 25-34, (2005)
  7. Lyovin, A., Kessler, B., Leben, W.: An introduction to the languages of the world. In: Oxford, New York: Oxford University Press, pp. 255, (2017)
  8. Yousfi, S.: Embedded Arabic text detection and recognition in videos. Ph.D. dissertation, University of de Lyon, Lyon, France, (2016)
  9. Elnagar, A., Al-Debsi, R., Einea, O.: Arabic text classification using deep learning models. In: Information Processing and Management, vol. 57(1), pp. 102121, (2020)
  10. Jain, M., Mathew, M., Jawahar, C. V.: "Unconstrained scene text and video text recognition for Arabic script. In: 2017 1st International Workshop on Arabic Script Analysis and Recognition, (2017)
  11. Tang, Z., Jialing, Y., Zhe, L., Fang, Q.: Grape disease image classification based on lightweight convolution neural networks and channel-wise attention. In: Computers and Electronics in Agriculture, vol. 178, pp. 105735, (2010)
  12. Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D Nonlinear Phenomena, vol. 404(8), p.132306, 2020.
  13. Grossberg, S.: Recurrent neural networks. Scholarpedia journal, vol.8(2), p.1888, (2013)
  14. Abu-Rabia, S.: The role of short vowels in reading arabic: a critical literature review. Journal of Psycholinguistic Research, vol.48(4), (2019)
  15. Abu-Rabia, S.: The effect of Arabic vowels on the reading comprehension of second- and sixth-grade native Arab children. Journal of Psycholinguistic Research, vol.28(1), pp.93-101, (1999) https://doi.org/10.1023/A:1023291620997
  16. Abu-Rabia, S.: Reading arabic texts: effects of text type, reader type and vowelisation. In: Reading and Writing, vol.10, pp.105-119, (1998) https://doi.org/10.1023/A:1007906222227
  17. Abu-Rabia, S.: The role of vowels in reading Semitic scripts: Data from Arabic and Hebrew. In: Reading and Writing, vol.14(1-2), pp.39-59, (2001) https://doi.org/10.1023/a:1008147606320
  18. Samkari, E.: Arabic Text with Harakat dataset. (2022) [Online]. Available:https://drive.google.com/drive/folders/1fdCPlDO3L5rTe-HuR26hqY5ojM9GCwYS?usp=sharing.
  19. iLoveIMG: The fastest free web app for easy image modification. (2022) [Online]. Available: https://www.iloveimg.com/
  20. Chung, J. Gulcehre, C., Cho, K. Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modelling. arXiv preprint, vol.1412.3555, (2014)
  21. Hochreiter, S., Schmidhuber, J.: Long short-term memory. In:Neural Computation, vol.9(8), pp.1735-1780,(1997) https://doi.org/10.1162/neco.1997.9.8.1735
  22. Graves, A., Fernandez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In: ICML 2006 - Proceedings of the 23rd International Conference on Machine Learning, (2006)
  23. A_K_Nain: OCR model for reading Captchas. (2022) [Online]. Available: https://keras.io/examples/vision/captcha_ocr/.
  24. Google Colab: Frequently Asked Questions. (2022) [Online]. Available: https://research.google.com/colaboratory/faq.html#resource-limits.