EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Image Processing and Clustering Framework for Unsupervised Crack Detection in Resistance Spot Welds

Ananta Dutta, Arka Ghosh, Angshuman Roy, Pankaj Shrivastava, Velaphi Msomi, S. S. K. Deepak, Kalyani Tiwari

Advances in Materials Science and Engineering · 2026-01 · 2026 (1)

DOI: 10.1155/amse/1491581 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Materials Science and Engineering, online erschienen am 15.06.2026. Verfasst von Ananta Dutta und 6 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Resistance spot welding (RSW) inspection increasingly relies on supervised deep learning models; however, such approaches require large labeled datasets, extensive retraining under changing conditions, and often lack interpretability. Despite their high reported accuracy, there remains a clear need for robust, unsupervised, and training‐free crack detection methods that can operate reliably under varying surface textures and illumination conditions. To address this gap, this study presents a fully unsupervised computer vision pipeline for the automated detection and delineation of cracks in resistance spot welds. The proposed framework integrates median absolute deviation (MAD)‐based adaptive thresholding for statistically robust crack candidate extraction, Laplacian filtering for edge enhancement, and Density‐Based Spatial Clustering of Applications with Noise (DBSCAN) to isolate true crack regions from noise without prior training. A region‐growing strategy ensures crack continuity, followed by contour delineation for precise visualization. Experimental evaluation on representative weld images demonstrates that the pipeline effectively suppresses surface noise, isolates dominant crack structures, and produces continuous and accurately delineated crack boundaries without requiring labeled data. By eliminating dataset dependency while maintaining reliable detection performance, the proposed approach provides an interpretable, scalable, and cost‐effective alternative for automated nondestructive weld inspection, with strong potential for real‐time industrial deployment.

Zitieren

APA

Dutta, A., Ghosh, A., Roy, A., Shrivastava, P., Msomi, V., Deepak, S. S. K., & Tiwari, K. (2026). A Hybrid Image Processing and Clustering Framework for Unsupervised Crack Detection in Resistance Spot Welds. Advances in Materials Science and Engineering, 2026(1). https://doi.org/10.1155/amse/1491581

Vancouver

Dutta A, Ghosh A, Roy A, Shrivastava P, Msomi V, Deepak SSK, et al. A Hybrid Image Processing and Clustering Framework for Unsupervised Crack Detection in Resistance Spot Welds. Advances in Materials Science and Engineering. 2026;2026(1). doi:10.1155/amse/1491581

BibTeX
@article{Dutta2026,
  author = {Dutta, Ananta and Ghosh, Arka and Roy, Angshuman and Shrivastava, Pankaj and Msomi, Velaphi and Deepak, S. S. K. and Tiwari, Kalyani},
  title = {A Hybrid Image Processing and Clustering Framework for Unsupervised Crack Detection in Resistance Spot Welds},
  journal = {Advances in Materials Science and Engineering},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/amse/1491581}
}
Kostenlos starten →