计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230100100-7.doi: 10.11896/jsjkx.230100100

• 图像处理&多媒体技术 • 上一篇    下一篇

基于改进YOLOv4的磁瓦缺陷检测算法

张晓晓, 邓承志, 吴朝明, 曹春阳, 胡诚   

  1. 南昌工程学院信息工程学院 南昌 330099
  • 发布日期:2023-11-09
  • 通讯作者: 邓承志(dengcz@nit.edu.cn)
  • 作者简介:(zhangxiaoxiao_666@163.com)
  • 基金资助:
    江西级研究生创新专项基金项目(YC2021-S184);南昌工程学院研究生创新专项计划项目(YJSCX202130)

Magnetic Tile Defect Detection Algorithm Based on Improved YOLOv4

ZHANG Xiaoxiao, DENG Chengzhi, WU Zhaoming, CAO Chunyang, HU Cheng   

  1. School of Information Engineering,Nanchang Institute of Technology,Nanchang 330099,China
  • Published:2023-11-09
  • About author:ZHANG Xiaoxiao,born in 1992,MS candidate.Her main research interests include deep learning and computer vision.
    DENG Chengzhi,born in 1964,Ph.D,professor,master supervisor.His main research interests include RS-image processing and image processing.
  • Supported by:
    Jiangxi Province Postgraduate Innovation Special Fund Project(YC2021-S184) and Nanchang Institute of Tech-nology Postgraduate Innovation Special Fund Project(YJSCX202130).

PDF (PC)

186

摘要： 磁瓦在生产制造过程中会因为工艺问题产生各种不同的缺陷,传统检测算法检测速度慢、精度低,为了实现磁瓦表面缺陷快速有效的检测,文中提出了一种改进YOLOv4算法的磁瓦缺陷检测方法。首先将scSE注意力模块嵌入特征提取主干网络中的CSPnet的残差单元中,增强小目标的空间特征和通道特征;其次,采用空洞卷积空间池化金字塔(ASPP)模块代替原有SPP模块,增大卷积核感受野,更多地保留图像细节并增强信息相关性;最后,在颈部部分用深度可分离卷积替换5次卷积块中的传统卷积,以此来更好地对特征信息进行提取,减小模型的参数量。实验结果表明,改进的YOLOv4算法对磁瓦表面缺陷检测的平均精度值达到96.67%,检测速度为44 ms,模型大小为249 MB,明显优于原始算法,具有较高的检测精度和实用性。关键词:缺陷检测;YOLOv4;scSE注意力;空洞卷积池化;深度可分离

关键词: 缺陷检测, YOLOv4, scSE注意力, 空洞卷积池化, 深度可分离

Abstract: Various defects occur in the manufacturing process of magnetic tiledue to process problems,and traditional detection algorithms have slow detection speed and low accuracy.In order to achieve fast and effective detection of surface defects of magnetic tiles,this paper proposes a defect detection method for magnetic tiles with improved YOLOv4 algorithm.Firstly,the scSE attention module is embedded in the residual unit of CSPnet in the feature extraction backbone network to enhance the spatial features and channel features of small targets.Secondly,the empty convolutional space pooling pyramid(ASPP) module is used instead of the original SPP module to increase the perceptual field of convolutional kernel,retain more image details and enhance information relevance.Finally,the traditional convolution in the five convolution blocks is replaced by the depth-separable convolution in the neck part to better extract the feature information and reduce the number of parameters of the model.Experimental results show that the improved YOLOv4 algorithm achieves an average accuracy value of 96.67%,a detection speed of 44 ms,and a model size of 249 MB.It is significantly better than the original algorithm and has higher detection accuracy and practicality.

Key words: Defect detection, YOLOv4, scSE attention, Void convolution pooling, Depth-separabl

中图分类号: 

  • TP391
[1]LIU C,ZHANG J,LIN J P.Detection and Identification of Surface Defects of Magnetic Tile Based on Neural Network[J].Surface Technology,2019,48(8):330-339.
[2]BHARATI P,PRAMANIK A.Deep learning techniques－R-CNN to mask R-CNN:a survey[C]//Computational Intelligence in Pattern Recognition(CIPR 2019).2020:657-668.
[3]GIRSHICK R.Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:1440-1448.
[4]CHEN Y,LI W,SAKARIDIS C,et al.Domain adaptive faster r-cnn for object detection in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3339-3348.
[5]JIANG P,ERGU D,LIU F,et al.A Review of Yolo algorithm developments[J].Procedia Computer Science,2022,199:1066-1073.
[6]LOEY M,MANOGARAN G,TAHA M H N,et al.Fightingagainst COVID-19:A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection[J].Sustainable Cities and Society,2021,65:102600.
[7]CAO X,ZHANG F,YIC,et al.Wafer Surface Defect Detection Based On Improved YOLOv3 Network[C]//2020 5th International Conference on Mechanical,Control and Computer Engineering (ICMCCE).2020.
[8]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.Yolov4:Optimal speed and accuracy of object detection[J].arXiv:2004.10934,2020.
[9]WANG P,SHI H,YANG X,et al.Three-way k-means:integrating k-means and three-way decision[J].International Journal of Machine Learning and Cybernetics,2019,10:2767-2777.
[10]XIE H,LI Y,LI X,et al.A Method for Surface Defect Detection of Printed Circuit Board Based on Improved YOLOv4[C]//2021 IEEE 2nd International Conference on Big Data,Artificial Intelligence and Internet of Things Engineering (ICBAIE).IEEE,2021.
[11]CHEN Q,WANG P S,CHENG A D,et al.Robust one-stage object detection with location-aware classifiers[J].Pattern Recognition,2020,105.
[12]WANG C Y,BOCHKOVSKIY A,LIAO H Y M.Scaled-yolov4:Scaling cross stage partial network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13029-13038.
[13]LI G,SUO R,ZHAO G,et al.Real-time detection of kiwifruit flower and bud simultaneously in orchard using YOLOv4 for robotic pollination[J].Computers and Electronics in Agriculture,2022,193:106641.
[14]WANG C Y,LIAO H Y M,WU Y H,et al.CSPNet:A new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.2020:390-391.
[15]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[16]LIU S,QI L,QIN H,et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8759-8768.
[17]GHIASI G,LIN T Y,LE Q V.Nas-fpn:Learning scalable feature pyramid architecture for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:7036-7045.
[18]OBESO A M,BENOIS-PINEAU J,V?ZQUEZ M S G,et al.Visual vs internal attention mechanisms in deep neural networks for image classification and object de-tection[J].Pattern Recognition,2022,123:108411.
[19]KUMAR A,SINGH SODHI S.Classification of data on stackedautoencoder using modified sigmoid activation function[J].Journal of Intelligent & Fuzzy Systems,2023(Preprint):1-18.
[20]HANANDEH S,ARDAH A,ABU-FARSAKH M.Using artificial neural network and ge-netics algorithm to estimate the resi-lient modulus for stabilized subgrade and propose new empirical formula[J].Transportation Geotechnics,2020,24:100358.
[21]HUANG Y,QIU C,YUAN K.Surface defect saliency of magnetic tile[J].The Visual Computer,2020,36:85-96.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发