EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Damage Attention-Aware Dense Layered Framework for Surface Crack Classification

Molaka Maruthi, Munisamy Shyamala Devi, Young Choi, Chang-Yong Yi

Buildings · 09.06.2026 · 16 (12) · 2313

DOI: 10.3390/buildings16122313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 09.06.2026. Verfasst von Molaka Maruthi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate surface defect classification is a critical requirement in structural health monitoring and infrastructure inspection, where defects, including cracks, spalling, delamination and noncrack regions, often appear with low-contrast and complex background textures. Motivated by the need for a robust and discriminative framework that can enhance defect visibility and focus learning on damage-critical regions, this research proposes a novel damage-aware DenseNet-201 (DA-DenseNet-201) model for surface defect classification. As a critical novelty, a damage-aware adaptive contrast-limited adaptive histogram equalisation (DAC) filtering strategy is introduced as a preprocessing stage. The proposed DAC filter dynamically adjusts contrast enhancement parameters based on damage indicators, selectively amplifying crack edges and defect textures while preserving healthy surface regions and suppressing noise. Building on this method, enhanced images are processed using a pretrained DenseNet-201 backbone, retaining the benefits of dense feature propagation and efficient gradient flow. To strengthen the discriminative learning of DA-DenseNet-201 further, an attention refinement block is integrated into the network, combining channel attention to emphasise defect-relevant feature responses and spatial attention to localise damage regions accurately. In addition, a multiscale feature fusion mechanism aggregates feature maps from multiple dense blocks to capture fine-grained crack patterns, texture-level degradation and high-level semantic damage information. Extensive experiments conducted on surface defect datasets demonstrate its effectiveness, achieving a superior classification accuracy of 98.93%, along with notable improvements in sensitivity, specificity and the intersection over union compared with state-of-the-art models. These results confirm that the proposed DA-DenseNet-201 provides a reliable and high-performance solution for automated surface defect classification.

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Maruthi, M., Devi, M. S., Choi, Y., & Yi, C. (2026). Damage Attention-Aware Dense Layered Framework for Surface Crack Classification. Buildings, 16(12), 2313. https://doi.org/10.3390/buildings16122313

Vancouver

Maruthi M, Devi MS, Choi Y, Yi C. Damage Attention-Aware Dense Layered Framework for Surface Crack Classification. Buildings. 2026;16(12):2313. doi:10.3390/buildings16122313

BibTeX
@article{Maruthi2026,
  author = {Maruthi, Molaka and Devi, Munisamy Shyamala and Choi, Young and Yi, Chang-Yong},
  title = {Damage Attention-Aware Dense Layered Framework for Surface Crack Classification},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {2313},
  doi = {10.3390/buildings16122313}
}
Kostenlos starten →