EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion

Zarnab Kausar, Shaheryar Najam, Mohammed Alshehri, Yahya AlQahtani, Abdulmonem Alshahrani, Ahmad Jalal, Jeongmin Park

PeerJ Computer Science · 26.11.2025 · 11 · e3275

DOI: 10.7717/peerj-cs.3275 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 26.11.2025. Verfasst von Zarnab Kausar und 6 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sign language is a vital communication tool for individuals with hearing and speech impairments, yet Arabic Sign Language (ArSL) recognition remains challenging due to signer variability, occlusions, and limited benchmark datasets. To address these challenges, we propose a two-hand static and dynamic gesture recognition system that integrates keypoint-based descriptors (ORB (Oriented FAST and Rotated BRIEF), AKAZE (Accelerated-KAZE), SIFT (Scale-Invariant Feature Transform), and BRISK (Binary Robust Invariant Scalable Keypoints)) with shape-based features (smoothness, convexity, compactness, symmetry) for enhanced gesture discrimination. A distance map-based method is also used to extract fingertip keypoints by identifying local maxima from the hand centroid. An attention-enabled feature fusion strategy effectively combines these diverse features, and a long short-term memory (LSTM) network captures temporal dependencies in dynamic gestures for improved classification. Evaluated on KArSL-100, KArSL-190, and KArSL-502, the proposed system achieved 77.34%, 62.53%, and 47.58% accuracy, respectively, demonstrating its robustness in recognizing both static and dynamic ArSL gestures. These results highlight the effectiveness of combining spatial and temporal features, paving the way for more accurate and inclusive sign language recognition systems.

Zitieren

APA

Kausar, Z., Najam, S., Alshehri, M., AlQahtani, Y., Alshahrani, A., Jalal, A., & Park, J. (2025). Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion. PeerJ Computer Science, 11, e3275. https://doi.org/10.7717/peerj-cs.3275

Vancouver

Kausar Z, Najam S, Alshehri M, AlQahtani Y, Alshahrani A, Jalal A, et al. Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion. PeerJ Computer Science. 2025;11:e3275. doi:10.7717/peerj-cs.3275

BibTeX
@article{Kausar2025,
  author = {Kausar, Zarnab and Najam, Shaheryar and Alshehri, Mohammed and AlQahtani, Yahya and Alshahrani, Abdulmonem and Jalal, Ahmad and Park, Jeongmin},
  title = {Two-hand static and dynamic Arabic sign language recognition using keypoints and shape descriptors with attention-driven feature fusion},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3275},
  doi = {10.7717/peerj-cs.3275}
}
Kostenlos starten →