Cover
Vol. 21 No. 2 (2025)

Published: December 16, 2025

Pages: 54-63

Original Article

An Ensemble Transfer Learning Model for the Automatic Handwriting Recognition of Kurdish Letters

Abdalbasit Qadir 1 Peshraw Abdalla 2 Mazen Ghareb Dana Abd 3 Karwan HamaKarim
1Information Technology Department, University of Human Development, Sulaymaniyah, Iraq
2Computer Science Department, University of Halabja, Halabja, Iraq
3Computer Science Department, University of Human Development, Sulaymaniyah, Iraq
History
  • Received: October 10, 2023
  • Revised: December 11, 2023
  • Accepted: February 2, 2024
  • Available Online: January 18, 2025
DOI

https://doi.org/10.37917/ijeee.21.2.6

Abstract

Automatic handwriting recognition is a fundamental component of various applications in various fields. During the last three decades, it has become a challenging issue that has attracted much attention. Latin language handwriting recognition has been the primary focus of researchers. As for the Kurdish language, only a few researches have been conducted. This study uses a Kurdish character dataset, which contains 40,940 characters written by 390 native writers. We present an ensemble transfer learning-based model for automatically recognizing handwritten Kurdish letters using Densenet-201, InceptionV3, Xception, and an ensemble of these pre-trained models. The model’s performance and results obtained by the proposed ensemble model are promising, with a 97% accuracy rate, outperforming other studies on Kurdish character recognition.

Keywords

References

  1. A. S. Abdalkafor, “Survey for databases on arabic offline handwritten characters recognition system,” in 2018 1st International Conference on Computer Applications Information Security (ICCAIS), pp. 1–6, IEEE, 2018.
  2. U. Porwal, Z. Shi, and S. Setlur, “Machine learning in handwritten arabic text recognition,” in Handbook of Statistics, vol. 31, pp. 443–469, Elsevier, 2013.
  3. A. Baldominos, Y. Saez, and P. J. A. S. Isasi, “A survey of handwritten character recognition with mnist and emnist,” Applied Sciences, vol. 9, no. 15, p. 3169, 2019.
  4. M. R. et al., “A survey on using neural network based algorithms for hand written digit recognition,” Applied Sciences, vol. 9, no. 9, 2018.
  5. A. M. Mustafa and T. A. Rashid, “Kurdish stemmer preprocessing steps for improving information retrieval,” Journal of Information Science, vol. 44, no. 1, pp. 15–27, 2018.
  6. T. A. Rashid, A. M. Mustafa, and A. M. Saeed, “Automatic kurdish text classification using kdc 4007 dataset,” in International Conference on Emerging Internetworking, Data Web Technologies, pp. 187–198, Springer, 2017.
  7. P. A. A. et al., “A vast dataset for kurdish handwritten digits and isolated characters recognition,” Data in Brief, vol. 47, p. 109014, 2023.
  8. S. Badawi, A. M. Saeed, S. A. Ahmed, P. A. Abdalla, and D. A. Hassan, “Kurdish news dataset headlines (kndh) through multiclass classification,” Data in Brief, vol. 48, p. 109120, 2023.
  9. B. O. Mohammed, “Handwritten kurdish character recognition using geometric discretization feature,” International Journal of Computer Science Communication, vol. 4, pp. 51–55, 2013.
  10. B. Zebardast, I. Maleki, and A. J. I. Maroufi, “A novel multilayer perceptron artificial neural network based recognition for kurdish manuscript,” International Journal of Science and Technology, vol. 7, no. 3, p. 343, 2014.
  11. R. D. Zarro, M. A. J. E. S. Anwer, and I. J. Technology, “Recognition-based online kurdish character recognition using hidden markov model and harmony search,” Journal of Engineering Science and Technology, vol. 20, no. 2, pp. 783–794, 2017.
  12. S. Idrees and H. Hassani, “Exploiting script similarities to compensate for the large amount of data in training tesseract lstm: Towards kurdish ocr,” Applied Sciences, vol. 11, no. 20, p. 9752, 2021.
  13. R. M. Ahmed et al., “Kurdish handwritten character recognition using deep learning techniques,” Journal of Engineering Science and Technology, vol. 46, p. 119278, 2022.
  14. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826, 2016.
  15. P. A. Abdalla, A. M. Qadir, O. J. Rashid, K. M. H. Rawf, A. O. Abdulrahman, and B. A. Mohammed, “Deep transfer learning networks for brain tumor detection: The effect of mri patient image augmentation methods,” International Journal of Electronics and Communications, vol. 75, p. 83, 2021.
  16. T. Lu, B. Han, L. Chen, F. Yu, and C. J. S. R. Xue, “A generic intelligent tomato classification system for practical applications using densenet-201 with transfer learning,” Scientific Reports, vol. 11, no. 1, pp. 1–8, 2021.
  17. X. Yu, N. Zeng, S. Liu, and Y.-D. Zhang, “Utilization of densenet201 for diagnosis of breast abnormality,” Machine Vision and Applications, vol. 30, no. 7, pp. 1135–1144, 2019.
  18. S.-H. Wang and Y.-D. Zhang, “Densenet-201-based deep neural network with composite learning factor and precomputation for multiple sclerosis classification,” ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 16, no. 2s, pp. 1–19, 2020.
  19. R. M. Ahmed, T. A. Rashid, P. Fatah, A. Alsadoon, and S. Mirjalili, “An extensive dataset of handwritten central kurdish isolated characters,” Data in Brief, vol. 39, p. 107479, 2021.
  20. P. A. Abdalla and B. A. Mohammed, “Re: ‘An extensive dataset of handwritten central kurdish isolated characters by R. M. Ahmed et al., Data in Brief, 2021, 39, 107479’,” Data in Brief, vol. 51, 2023.
  21. M. Grandini, E. Bagli, and G. Visani, “Metrics for multi-class classification: an overview,” arXiv preprint arXiv:2008.05756, 2020.