首页|基于DCGAN和改进YOLOv5s的钢丝帘布缺陷检测方法

基于DCGAN和改进YOLOv5s的钢丝帘布缺陷检测方法

扫码查看
原文链接
  • 万方数据
  • 维普
为解决钢丝帘布表面缺陷检测准确率低且泛化能力不强的问题,提出了一种基于DCGAN和改进 YOLOv5 s的缺陷检测方法.首先,通过调整DCGAN网络参数并优化超参数,使生成器能够生成具有丰富特征和清晰纹理的钢丝帘布缺陷图像,从而扩充数据集;其次,采用K-means++算法对钢丝帘布缺陷数据重新聚类锚框,以获得更优的锚框参数,实现锚框与实际缺陷的精确匹配;然后,在 YOLOv5 s主干网络中的 C3 模块添加坐标注意力机制,以增强模型的特征提取能力和精确定位能力;最后,引入 MPDIoU损失函数替换 YOLOv5 s原损失函数,进一步提高检测精度.实验结果表明,在实测钢丝帘布缺陷数据集上,采用 DCGAN 数据增强和改进后的 YOLOv5 s 检测模型,缺陷检测平均精度提高了 6.6%,达到了 89.4%,并且检测准确率和召回率也有所提高.与其他主流检测模型相比,该模型不仅在检测速度上提高了约 30%,还保持较高的检测精度.在公开的 NEU-DET 数据集上,该模型的 mAP 值达到了82.6%,较原始 YOLOv5 s模型提高了 3.8%.
Defect detection method of steel cord based on DCGAN and improved YOLOv5s
In order to solve the problems of low detection accuracy and weak generalization ability of steel cord surface defects,a steel cord defect detection method based on DCGAN and improved YOLOv5s was proposed.Firstly,by adjusting DCGAN network parameters and optimizing hyperparameters,the generator can generate steel cord defect images with rich features and clear texture,thus expanding the data set.Secondly,the K-Means++ algorithm is used to re-cluster the anchor frame to obtain better anchor frame parameters and achieve accurate matching between anchor frame and actual defects.Then,coordinate attention mechanism was added to C3 module of YOLOv5s backbone network to enhance the feature extraction capability and accurate localization capability of the model.Finally,MPDIoU loss function is introduced to replace YOLOv5s original loss function to further improve the detection accuracy.The experimental results show that on the measured steel cord defect data set,the average accuracy of defect detection is increased by 6.6%,reaching 89.4%by using the YOLOv5s detection model enhanced and improved by DCGAN data,and the detection accuracy and recall rate are also improved.Compared with other mainstream detection models,this model not only improves the detection speed by about 30%,but also maintains high detection accuracy.On the publicly available NEU-DET dataset,the mAP value of this model reaches 82.6%,which is 3.8%higher than that of the original YOLOv5s model.

steel cord defect detectiongenerate adversarial networkK-means + +attention mechanismMPDIoU loss function

黄鹏、蔡露、陈彬、周益航、易冬旺

展开 >

桂林理工大学机械与控制工程学院 桂林 541000

钢丝帘布缺陷检测 生成对抗网络 K-means++ 注意力机制 MPDIoU损失函数

国家自然科学基金广西科技计划项目桂林市科学研究与技术开发计划项目桂林理工大学科研启动基金

72001054桂科AB2203504120210217-14GUTQDJJ20160140

2024

10.19651/j.cnki.emt.2314717

电子测量技术
北京无线电技术研究所

电子测量技术

CSTPCD北大核心
影响因子：1.166
ISSN：1002-7300
年,卷(期)：2024.47(3)
  • 27