Opto-Electronic Engineering, Volume. 52, Issue 1, 240250(2025)

PIC2f-YOLO: a lightweight method for the detection of metal surface defects

Yilun Hu1...2, Jun Yang2, Congyuan Xu2, Yajin Xia3 and Wenbin Deng2,* |Show fewer author(s)
Author Affiliations
  • 1College of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
  • 2College of Information Science and Engineering, Jiaxing University, Jiaxing, Zhejiang 314001, China
  • 3Haiyan ZhongDA METAL Electronic Material Co., LTD, Jiaxing, Zhejiang 314300, China
  • show less

    To address the low efficiency in metal surface defect detection, and the problems related to numerous model parameters and low precision, a lightweight detection method based on an improved YOLOv8n was proposed. The partially inverted bottleneck cross-stage partial fusion (PIC2f) module was introduced, replacing the bottleneck module with a partial IRMB bottleneck (PIBN) module. This combination of partial convolution and inverted residual blocks reduced the algorithm’s parameters and enhanced the model’s feature extraction ability. The attention-based intra-scale feature interaction (AIFI) module was applied, integrating location embedding and multi-head attention to improve the model’s small-target detection performance. Lastly, the average pooling down sampling (ADown) module replaced traditional convolution as the feature reduction module, reducing parameters and computational complexity while maintaining detection accuracy. The experimental results show that, compared to YOLOv8n, the PIC2f-YOLO method improves mAP50 by 2.7% on the NEU-DET steel defect dataset and reduces parameters by 0.403 M. Generalization experiments on aluminum sheet surface industrial defects, PASCAL VOC2012 and surface defects of strip alloy functional material datasets also confirm the method’s effectiveness.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Yilun Hu, Jun Yang, Congyuan Xu, Yajin Xia, Wenbin Deng. PIC2f-YOLO: a lightweight method for the detection of metal surface defects[J]. Opto-Electronic Engineering, 2025, 52(1): 240250

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Article

    Received: Oct. 23, 2024

    Accepted: Dec. 16, 2024

    Published Online: Feb. 21, 2025

    The Author Email: Deng Wenbin (邓文斌)

    DOI:10.12086/oee.2025.240250

    Topics