Abstract

Digitisation of Ottoman Turkish archival documents is of great importance for historical research. In this study, a dataset of 62,000 character samples was created from handwritten documents in riq'a and naskh scripts. A multi-task convolutional neural network that accounts for position-dependent letter forms is proposed. The model achieved 96.4% accuracy at the character level and 88.7% at the word level. Most recognition errors were found to stem from diacritics and ligatures.

Keywords:optical character recognitionOttoman Turkishconvolutional neural networkdigital humanities

Full Text

PDF (TR) Download · 8 KB

Declarations

Ethics Approval
Bu çalışma etik kurul onayı gerektirmemektedir.
Conflict of Interest
Yazarlar herhangi bir çıkar çatışması olmadığını beyan eder.
Funding
Bu çalışma Selçuk Üniversitesi BAP Koordinatörlüğü tarafından desteklenmiştir (Proje No: 24015).

References 5

  1. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.
  2. Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.
  3. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770–778). https://doi.org/10.1109/CVPR.2016.90
  4. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958.
  5. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

How to Cite

Çelik, D., & Arslan, C. (2026). Character Recognition in Ottoman Turkish Handwritten Documents Using Convolutional Neural Networks. International Journal of Science and Technology Research, 8(1), 15–31. https://doi.org/10.99999/ubtad.2026.16
BibTeX RIS (EndNote, Zotero, Mendeley)

License

CC BY 4.0

© 2026 Deniz Çelik, Cem Arslan. This article is distributed under the terms of the CC BY 4.0 license, which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. License text