EUVIMEDEUVIMED entdecken
Crossref

Dynamic Adaptive Angular Margin Network (DAAM-Net) for Quality-Aware Face Recognition

K. Sadhana, T. Shreekumar

AVE Trends in Intelligent Computer Letters · 2025

DOI: 10.64091/aticl.2025.000228 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AVE Trends in Intelligent Computer Letters, 2025. Verfasst von K. Sadhana und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Face recognition systems often experience a significant drop in accuracy when images contain blur, noise, extreme pose, shadows, or occlusions. Conventional margin-based models treat all samples equally, thereby allowing degraded inputs to distort the embedding space during training. This work presents DAAM Net, a quality-aware face recognition framework that incorporates visual reliability directly into the margin learning process. The method combines a feature-extraction network with a lightweight quality-estimation module that assesses the clarity of each input image. This score is then used to generate a dynamic angular margin that strengthens discrimination for reliable samples and reduces the influence of those affected by degradation. A quality-regulated angular loss integrates these margins into the optimisation process, leading to more stable and compact identity representations. Experiments conducted on a curated subset of VGGFace2 show that DAAM Net achieves 97.6 per cent accuracy, outperforming fixed-margin methods such as ArcFace, CosFace, and SphereFace, with particularly strong gains on low-quality images. Ablation studies confirm the complementary value of explicit quality estimation and dynamic margin adjustment. The results indicate that incorporating visual quality into the training objective is an effective strategy for improving robustness in unconstrained face recognition scenarios.

Zitieren

APA

Sadhana, K., & Shreekumar, T. (2025). Dynamic Adaptive Angular Margin Network (DAAM-Net) for Quality-Aware Face Recognition. AVE Trends in Intelligent Computer Letters. https://doi.org/10.64091/aticl.2025.000228

Vancouver

Sadhana K, Shreekumar T. Dynamic Adaptive Angular Margin Network (DAAM-Net) for Quality-Aware Face Recognition. AVE Trends in Intelligent Computer Letters. 2025. doi:10.64091/aticl.2025.000228

BibTeX
@article{Sadhana2025,
  author = {Sadhana, K. and Shreekumar, T.},
  title = {Dynamic Adaptive Angular Margin Network (DAAM-Net) for Quality-Aware Face Recognition},
  journal = {AVE Trends in Intelligent Computer Letters},
  year = {2025},
  doi = {10.64091/aticl.2025.000228}
}
Kostenlos starten →