@inproceedings{gurer-etal-2025-text,
    title = "Text Extraction and Script Completion in Images of {A}rabic Script-Based Calligraphy: A Thesis Proposal",
    author = {G{\"u}rer, Dilara Zeynep  and
      Atlamaz, {\"U}mit  and
      {\"O}zate{\c{s}}, {\c{S}}aziye Bet{\"u}l},
    editor = "Ebrahimi, Abteen  and
      Haider, Samar  and
      Liu, Emmy  and
      Haider, Sammar  and
      Leonor Pacheco, Maria  and
      Wein, Shira",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
    month = apr,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.naacl-srw.25/",
    doi = "10.18653/v1/2025.naacl-srw.25",
    pages = "253--259",
    ISBN = "979-8-89176-192-6",
    abstract = "Arabic calligraphy carries rich historical information and meaning. However, the complexity of its artistic elements and the absence of a consistent baseline make text extraction from such works highly challenging. In this paper, we provide an in-depth analysis of the unique obstacles in processing and interpreting these images, including the variability in calligraphic styles, the influence of artistic distortions, and the challenges posed by missing or damaged text elements. We explore potential solutions by leveraging state-of-the-art architectures and deep learning models, including visual language models, to improve text extraction and script completion."
}