EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Historical Manuscripts Analysis: A Deep Learning System for Writer Identification Using Intelligent Feature Selection with Vision Transformers

Merouane Boudraa, Akram Bennour iD, Mouaaz Nahas iD, Rashiq Rafiq Marie, Mohammed Al-Sarem iD

Journal of Imaging · 19.06.2025 · 11 (6) · 204

DOI: 10.3390/jimaging11060204 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 19.06.2025. Verfasst von Merouane Boudraa und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Mathematics, Informatics and Systems (LAMIS), Echahid Cheikh Larbi Tebessi University, Tebessa 12000, Algeria. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Umm Al-Qura University, Saudi Arabia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying the scriptwriter in historical manuscripts is crucial for historians, providing valuable insights into historical contexts and aiding in solving historical mysteries. This research presents a robust deep learning system designed for classifying historical manuscripts by writer, employing intelligent feature selection and vision transformers. Our methodology meticulously investigates the efficacy of both handcrafted techniques for feature identification and deep learning architectures for classification tasks in writer identification. The initial preprocessing phase involves thorough document refinement using bilateral filtering for denoising and Otsu thresholding for binarization, ensuring document clarity and consistency for subsequent feature detection. We utilize the FAST detector for feature detection, extracting keypoints representing handwriting styles, followed by clustering with the k-means algorithm to obtain meaningful patches of uniform size. This strategic clustering minimizes redundancy and creates a comprehensive dataset ideal for deep learning classification tasks. Leveraging vision transformer models, our methodology effectively learns complex patterns and features from extracted patches, enabling precise identification of writers across historical manuscripts. This study pioneers the application of vision transformers in historical document analysis, showcasing superior performance on the “ICDAR 2017” dataset compared to state-of-the-art methods and affirming our approach as a robust tool for historical manuscript analysis.

Schlagwörter

Stichwörter der Autor:innen

deep learninghistorical manuscriptsintelligent featurestransfer learningvision transformerswriter identification

Autor:innen und Institutionen

  • Laboratory of Mathematics, Informatics and Systems (LAMIS), Echahid Cheikh Larbi Tebessi University, Tebessa 12000, Algeria.
  • Department of Electrical Engineering, Umm Al-Qura University, Makkah 21955, Saudi Arabia.
  • College of Computer Science and Engineering, Taibah University, Medina 41477, Saudi Arabia.
  • Department of Information Technology, Aylol University College, Yarim 547, Yemen.

ORCID-Profile: Akram Bennour, Mouaaz Nahas, Mohammed Al-Sarem

Förderung

  • Umm Al-Qura University, Saudi Arabia

Zitieren

APA

Boudraa, M., Bennour, A., Nahas, M., Marie, R. R., & Al-Sarem, M. (2025). Historical Manuscripts Analysis: A Deep Learning System for Writer Identification Using Intelligent Feature Selection with Vision Transformers. Journal of Imaging, 11(6), 204. https://doi.org/10.3390/jimaging11060204

Vancouver

Boudraa M, Bennour A, Nahas M, Marie RR, Al-Sarem M. Historical Manuscripts Analysis: A Deep Learning System for Writer Identification Using Intelligent Feature Selection with Vision Transformers. Journal of Imaging. 2025;11(6):204. doi:10.3390/jimaging11060204

BibTeX
@article{Boudraa2025,
  author = {Boudraa, Merouane and Bennour, Akram and Nahas, Mouaaz and Marie, Rashiq Rafiq and Al-Sarem, Mohammed},
  title = {Historical Manuscripts Analysis: A Deep Learning System for Writer Identification Using Intelligent Feature Selection with Vision Transformers},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {6},
  pages = {204},
  doi = {10.3390/jimaging11060204}
}
Kostenlos starten →