Scholarlink

<p>Defect detection is vital for product quality in industrial production, yet current surface defect detection technologies struggle with diverse defect types and complex backgrounds. The challenge intensifies with multi-scale small targets, leading to significantly reduced detection performance. Therefore, this paper proposes the EPSC-YOLO algorithm to improve the efficiency and accuracy of defect detection. The algorithm first introduces multi-scale attention modules and uses two newly designed pyramid convolutions in the backbone network to better identify multi-scale defects; Secondly, Soft-NMS is introduced to replace traditional NMS, which can reduce information loss and improve multi-target detection accuracy by smoothing and suppressing the scores of overlapping boxes. In addition, a new convolutional attention module, CISBA, is designed to enhance the detection capability of small targets in complex backgrounds. In the end, we validate the effectiveness of EPSC-YOLO on NEU-DET and GC10-DET datasets. The experimental results show that, compared to YOLOv9c, <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_91930_Article_IEq1.gif" Format="GIF" Height="21" Rendition="HTML" Resolution="72" Type="Linedraw" Width="60" /> </InlineMediaObject> <EquationSource Format="TEX">\(mAP^{val}_{50}\)</EquationSource> </InlineEquation> increases by 2% and 2.4%, and <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_91930_Article_IEq2.gif" Format="GIF" Height="21" Rendition="HTML" Resolution="72" Type="Linedraw" Width="67" /> </InlineMediaObject> <EquationSource Format="TEX">\(mAP^{val}_{50:95}\)</EquationSource> </InlineEquation> increases by 5.1% and 2.4%, respectively. Meanwhile, EPSC-YOLO demonstrates superior accuracy and significant advantages in real-time detection of surface defects on products compared to algorithms such as YOLOv10 and MSFT-YOLO.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A high precision YOLO model for surface defect detection based on PyConv and CISBA

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月6日

查看全文
  • Shufen Ruan,
  • Chenmei Zhan,
  • Bo Liu,
  • Quan Wan,
  • Kunfang Song

摘要

Defect detection is vital for product quality in industrial production, yet current surface defect detection technologies struggle with diverse defect types and complex backgrounds. The challenge intensifies with multi-scale small targets, leading to significantly reduced detection performance. Therefore, this paper proposes the EPSC-YOLO algorithm to improve the efficiency and accuracy of defect detection. The algorithm first introduces multi-scale attention modules and uses two newly designed pyramid convolutions in the backbone network to better identify multi-scale defects; Secondly, Soft-NMS is introduced to replace traditional NMS, which can reduce information loss and improve multi-target detection accuracy by smoothing and suppressing the scores of overlapping boxes. In addition, a new convolutional attention module, CISBA, is designed to enhance the detection capability of small targets in complex backgrounds. In the end, we validate the effectiveness of EPSC-YOLO on NEU-DET and GC10-DET datasets. The experimental results show that, compared to YOLOv9c, \(mAP^{val}_{50}\) increases by 2% and 2.4%, and \(mAP^{val}_{50:95}\) increases by 5.1% and 2.4%, respectively. Meanwhile, EPSC-YOLO demonstrates superior accuracy and significant advantages in real-time detection of surface defects on products compared to algorithms such as YOLOv10 and MSFT-YOLO.