郑州大学学报（工学版）2025，Vol.46Issue(5)：18-25,8.DOI:10.13705/j.issn.1671-6833.2025.02.020
改进YOLOv5的工业产品表面缺陷检测方法
Industrial Product Surface Defect Detection of Improved YOLOv5
摘要
Abstract
Aiming at the problem of limited resources and low contrast of surface defect images in industrial scenari-os,an improved YOLOv5 industrial product surface defect detection method was proposed.This method first intro-duced a receptive field enhancement module in the backbone network to extract richer visual features from different levels of receptive fields.Secondly,a shuffle attention module was added to the feature fusion network to more ef-fectively fuse feature maps of different dimensions.Finally,a task decoupling detection head was adopted,allowing the classification and regression tasks to use independent networks for prediction,reducing mutual interference and improving detection accuracy.The experimental results showed that the parameter and computational complexity of this network were lower than models such as YOLOX,YOLOv7,and deformable DETR.On the pipeline Digital Ray(DR)defect image dataset and NEU-DET dataset,the mAP@0.5 were increased by 2.23 percentage points and 2.99 percentage points respectively,balancing the requirements for real-time and accurate defect detection in industrial scenarios.关键词
表面缺陷检测/计算机视觉/多尺度特征提取/注意力机制/解耦检测头Key words
surface defect detection/computer vision/multi-scale feature extraction/attention mechanism/decou-pling detection head分类
信息技术与安全科学引用本文复制引用
刘兆英,陈志远,张婷,时亚南,陈迎春..改进YOLOv5的工业产品表面缺陷检测方法[J].郑州大学学报（工学版）,2025,46(5):18-25,8.基金项目
新疆维吾尔自治区自然科学基金资助项目(2023D01A22) 本文受国家市场监管总局科技计划项目(2021MK119)的支持 （2023D01A22）
