IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v13y2025i5p831-d1603762.html
   My bibliography  Save this article

DGYOLOv8: An Enhanced Model for Steel Surface Defect Detection Based on YOLOv8

Author

Listed:
  • Guanlin Zhu

    (School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China)

  • Honggang Qi

    (School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China)

  • Ke Lv

    (School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 101408, China)

Abstract

The application of deep learning-based defect detection models significantly reduces the workload of workers and enhances the efficiency of inspections. In this paper, an enhanced YOLOv8 model (DCNv4_C2f + GAM + InnerMPDIoU + YOLOv8, hereafter referred to as DGYOLOv8) is developed to tackle the challenges of object detection in steel surface defect detection tasks. DGYOLOv8 incorporates a deformable convolution C2f (DCNv4_C2f) module into the backbone network to allow adaptive adjustment of the receptive field. Additionally, it integrates a Gate Attention Module (GAM) within the spatial and channel attention mechanisms, enhancing feature selection through a gating mechanism that strengthens key features, thereby improving the model’s generalization and interpretability. The InnerMPDIoU, which incorporates the latest Inner concepts, enhances detection accuracy and the ability to handle detailed aspects effectively. This model helps to address the limitations of current networks. Experimental results show improvements in precision (P), recall (R), and mean average precision (mAP) compared to existing models.

Suggested Citation

  • Guanlin Zhu & Honggang Qi & Ke Lv, 2025. "DGYOLOv8: An Enhanced Model for Steel Surface Defect Detection Based on YOLOv8," Mathematics, MDPI, vol. 13(5), pages 1-16, March.
  • Handle: RePEc:gam:jmathe:v:13:y:2025:i:5:p:831-:d:1603762
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/13/5/831/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/13/5/831/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Muhammad Zohaib & Muhammad Asim & Mohammed ELAffendi, 2024. "Enhancing Emergency Vehicle Detection: A Deep Learning Approach with Multimodal Fusion," Mathematics, MDPI, vol. 12(10), pages 1-23, May.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.

      Corrections

      All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:13:y:2025:i:5:p:831-:d:1603762. See general information about how to correct material in RePEc.

      If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

      If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

      If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

      For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

      Please note that corrections may take a couple of weeks to filter through the various RePEc services.

      IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.