Steel Surface Defect Segmentation Using U-Net with SLMA-Gray Attention and AdamW Optimization

Abstract

Rust detection on metal surfaces is a challenging task in industrial maintenance and quality control. This paper proposes an improved U-Net segmentation method that enhances the accuracy of surface defect detection in steel materials. This paper proposes an improved U-Net model for steel surface defect segmentation. We introduce a novel Spatial-Channel Gray-Level Mixed Attention mechanism (SLMA-Gray) to enhance defect saliency in grayscale images and employ the AdamW optimizer to improve generalization. Experiments on the NEU-DET dataset show our method significantly outperforms the original U-Net, with increases of 5.29% in precision, 18.84% in recall, 3.34% in accuracy, 15.17% in Dice, and 18.18% in IoU.

Authors

  • Ru Yang
  • Zhang Chen
  • Zhentao Qin School of Mathmatics and Computer Science, Panzhihua University, Panzhihua 617000, China
  • Yuanjie Lu
  • Lai Qi

DOI:

https://doi.org/10.31449/inf.v49i31.10673

Downloads

Published

2025-12-23

Issue

Vol. 49 No. 31 (2025): Online-only issue

Section

Online-only

License

I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.

I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.

In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.

I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal.  The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.


Copyright ©  Slovenian Society Informatika