EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

$$\hbox {D}^2$$RSM-former: a directional deformable refinement transformer with soft-edge smooth span mask for robust handwritten text recognition

Yao Wei, Haicheng Qu, Jiandong Li

Complex & Intelligent Systems · 2027-01 · 13 (1)

DOI: 10.1007/s40747-026-02477-z ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 20.08.2026. Verfasst von Yao Wei und 2 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Scientific Research Project of Liaoning Provincial Department of Education, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Handwritten text recognition technology plays a crucial role in historical document digitization, archive management systems, and cultural heritage preservation. Although existing methods based on Convolutional Neural Networks and Vision Transformers have achieved remarkable progress in feature extraction and global modeling, they still exhibit limitations when addressing inherent challenges of handwritten text, including stroke deformation, character adhesion, and cross-lingual robustness. To address these challenges, we propose a Directional Deformable Refinement Transformer with Soft-edge Smooth Span Mask for Robust Handwritten Text Recognition ( $$\hbox {D}^2$$ D 2 RSM-Former), which innovatively integrates a Hierarchical Adaptive Directional Deformable Feature Extractor (HADD-FE), a Soft-edge Smooth Span Mask (SSSM) strategy, and a Heterogeneous Interactive Refinement Encoder (HIREncoder). HADD-FE dynamically adjusts receptive field configurations through an adaptive directional deformable mechanism, effectively capturing anisotropic features of handwritten text. The SSSM enhances generalization through smooth boundary transitions and adaptive length sampling. HIREncoder achieves synergistic modeling of local–global features through dialogic head contextual attention and heterogeneous iterative refinement mechanisms. Extensive experiments on six benchmark datasets demonstrate that, without relying on any pre-training or synthetic data, $$\hbox {D}^2$$ D 2 RSM-Former achieves state-of-the-art performance on READ2016, LAM, and IAM datasets, while also demonstrating highly competitive results on RIMES2011, BRESSAY, and VOHTR2018 datasets.

Förderung

  • Basic Scientific Research Project of Liaoning Provincial Department of Education
  • National Natural Science Foundation of China

Zitieren

APA

Wei, Y., Qu, H., & Li, J. (2027). $$\hbox {D}^2$$RSM-former: a directional deformable refinement transformer with soft-edge smooth span mask for robust handwritten text recognition. Complex & Intelligent Systems, 13(1). https://doi.org/10.1007/s40747-026-02477-z

Vancouver

Wei Y, Qu H, Li J. $$\hbox {D}^2$$RSM-former: a directional deformable refinement transformer with soft-edge smooth span mask for robust handwritten text recognition. Complex & Intelligent Systems. 2027;13(1). doi:10.1007/s40747-026-02477-z

BibTeX
@article{Wei2027,
  author = {Wei, Yao and Qu, Haicheng and Li, Jiandong},
  title = {$$\hbox D^2$$RSM-former: a directional deformable refinement transformer with soft-edge smooth span mask for robust handwritten text recognition},
  journal = {Complex & Intelligent Systems},
  year = {2027},
  volume = {13},
  number = {1},
  doi = {10.1007/s40747-026-02477-z}
}
Kostenlos starten →