Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Fast and accurate detection of surface defect based on improved YOLOv4

Fast and accurate detection of surface defect based on improved YOLOv4 The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.Design/methodology/approachOn the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.FindingsThe effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.Originality/valueThis paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Assembly Automation Emerald Publishing

Fast and accurate detection of surface defect based on improved YOLOv4

Lian, Jiawei; He, Junhong; Niu, Yun; Wang, Tianze
Assembly Automation , Volume 42 (1): 13 – Jan 11, 2022
Download PDF
13 pages

Loading next page...
 
/lp/emerald-publishing/fast-and-accurate-detection-of-surface-defect-based-on-improved-yolov4-f3BE0jb40X
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0144-5154
DOI
10.1108/aa-04-2021-0044
Publisher site
See Article on Publisher Site

Abstract

The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.Design/methodology/approachOn the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.FindingsThe effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.Originality/valueThis paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

Journal

Assembly Automation – Emerald Publishing

Published: Jan 11, 2022

Keywords: Surface defect detection; Tiny defect; YOLOv4; Multi-dimensional compression; Prediction scale optimization

References

  • Convolutional neural networks for speech recognition
    Abdel-Hamid, O.; Mohamed, A.; Jiang, H.; Deng, L.; Penn, G.; Yu, D.
  • Triplet-Graph reasoning network for Few-Shot metal generic surface defect segmentation
    Bao, Y.
  • YOLOv4: optimal speed and accuracy of object detection
    Bochkovskiy, A.; Wang, C.; Liao, H.
  • Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network
    Chen, J.; Liu, Z.; Wang, H.; Núñez, A.; Han, Z.
  • ThriftyNets: convolutional neural networks with tiny parameter budget
    Coiffier, G.; Boukli Hacene, G.; Gripon, V.
  • Deep active learning for civil infrastructure defect detection and classification
    Feng, C.; Liu, M.; Kao, C.; Lee, T.
  • Deep residual learning for image recognition
    He, K.; Zhang, X.; Ren, S.; Sun, J.
  • Distilling the knowledge in a neural network
    Hinton, G.; Vinyals, O.; Dean, J.
  • MobileNets: efficient convolutional neural networks for mobile vision applications
    Howard, A.; Zhu, M.; Chen, B.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H.
  • Network trimming: a Data-Driven neuron pruning approach towards efficient deep architectures
    Hu, H.; Peng, R.; Tai, Y.; Tang, C.
  • An analysis of convolutional neural networks for speech recognition
    Huang, J.; Li, J.; Gong, Y.
  • Internal crack detection of castings: a study based on relief algorithm and Adaboost-SVM
    Jin, C.; Kong, X.; Chang, J.; Cheng, H.; Liu, X.
  • Convolutional neural networks for sentence classification
    Kim, Y.
  • A convolutional neural network Cascade for face detection
    Li, H.; Lin, Z.; Shen, X.; Brandt, J.; Hua, G.
  • SSD: single shot MultiBox detector
    Liu, W.
  • Improved cross pattern approach for steel surface defect recognition
    Mentouri, Z.; Doghmane, H.; Moussaoui, A.; Bourouba, H.
  • Unsupervised saliency detection of rail surface defects using stereoscopic images
    Niu, M.; Song, K.; Huang, L.; Wang, Q.; Yan, Y.; Meng, Q.
  • Faster R-CNN: towards real-time object detection with region proposal networks
    Ren, S.; He, K.; Girshick, R.; Sun, J.
  • Very deep convolutional networks for large-scale image recognition
    Simonyan, K.; Zisserman, A.
  • Going deeper with convolutions
    Szegedy, C.
  • Detection of power line insulator defects using aerial images analyzed with convolutional neural networks
    Tao, X.; Zhang, D.; Wang, Z.; Liu, X.; Zhang, H.; Xu, D.
  • Learning structured sparsity in deep neural networks
    Wen, W.; Wu, C.; Wang, Y.; Chen, Y.; Li, H.
  • An end-to-end learning method for industrial defect detection
    Wu, Y.; Guo, D.; Liu, H.; Huang, Y.
  • Deep k-means: re-training and parameter sharing with harder cluster assignments for compressing deep convolutions
    Wu, J.; Wang, Y.; Wu, Z.; Wang, Z.; Veeraraghavan, A.; Lin, Y.
  • Glass surface defect detection method based on multiscale convolutional neural network
    Xiong, H.; Fan, C.; Zhao, S.; Yu, Y.
  • Fully convolutional networks for surface defect inspection in industrial environment
    Yu, Z.; Wu, X.; Gu, X.
  • Two deep learning networks for rail surface defect inspection of limited samples with Line-Level label
    Zhang, D.; Song, K.; Wang, Q.; He, Y.; Wen, X.; Yan, Y.
  • A generic SemiSupervised deep learning based approach for automated surface inspection
    Zheng, X.; Wang, H.; Chen, J.; Kong, Y.; Zheng, S.
  • Joint face detection and alignment using multitask cascaded convolutional networks
    Zhang, K.; Zhang, Z.; Li, Z.; Qiao, Y.