EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

EASE-DET: An efficient adaptive sparse enhancement algorithm for steel surface defect detection

Yong-Ting He, Jin-Shan Zhang

European Journal of Mathematics and Applications · 13.11.2026 · 6 · 16

DOI: 10.28919/ejma.2026.6.16 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Mathematics and Applications, online erschienen am 13.11.2026. Verfasst von Yong-Ting He und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Steel surface defects pose a persistent threat to product quality and structural integrity. Standard detection networks remain limited in three respects: the backbone struggles to discriminate defects from visually similar background textures; cross-scale fusion in the feature pyramid introduces spatial misalignment, degrading localization accuracy for small objects; and per-scale parameterization of the detection head causes redundancy while offering insufficient sensitivity to defect edge gradients. Taking YOLO11 as the baseline, this paper introduces an Adaptive Position-aware Feature Extraction Module to strengthen global context modeling in the backbone, an Adaptive Context-aware Feature Pyramid Network to improve cross-scale alignment, and an Efficient Shared Detection Head that combines parameter sharing with multi-directional differential convolution for lightweight edge enhancement. On the NEU-DET dataset, EASE-DET achieves 78.3% mAP@0.5, a 3.7-point improvement over the baseline. Cross-domain evaluation on GC10-DET further validates the generalization capability of the proposed method.

Zitieren

APA

He, Y., & Zhang, J. (2026). EASE-DET: An efficient adaptive sparse enhancement algorithm for steel surface defect detection. European Journal of Mathematics and Applications, 6, 16. https://doi.org/10.28919/ejma.2026.6.16

Vancouver

He Y, Zhang J. EASE-DET: An efficient adaptive sparse enhancement algorithm for steel surface defect detection. European Journal of Mathematics and Applications. 2026;6:16. doi:10.28919/ejma.2026.6.16

BibTeX
@article{He2026,
  author = {He, Yong-Ting and Zhang, Jin-Shan},
  title = {EASE-DET: An efficient adaptive sparse enhancement algorithm for steel surface defect detection},
  journal = {European Journal of Mathematics and Applications},
  year = {2026},
  volume = {6},
  pages = {16},
  doi = {10.28919/ejma.2026.6.16}
}
Kostenlos starten →