Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Defect Detection Algorithm of Denim Fabric Based on Cascading Feature Extraction Architecture

  • Shuangbao, Ma (School of Mechanical Engineering and Automation, Wuhan Textile University) ;
  • Renchao, Zhang (School of Mechanical Engineering and Automation, Wuhan Textile University) ;
  • Yujie, Dong (School of Mechanical Engineering and Automation, Wuhan Textile University) ;
  • Yuhui, Feng (School of Mechanical Engineering and Automation, Wuhan Textile University) ;
  • Guoqin, Zhang (School of Electronics and Electrical Engineering, Wuhan Textile University)
  • Received : 2022.02.16
  • Accepted : 2022.07.08
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denim fabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extraction architecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the large dataset ImageNet and uses its portability to train the defect detection classifier and the defect recognition classifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layer were retrained and adjusted from of these two training models on the high-definition fabric defect dataset. The last step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and other feature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show that the defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increased by 1-3 percentage points.

Keywords

Acknowledgement

This paper is supported by grants from State Key Laboratory of New Textile Materials and Advanced Processing Technologies in Wuhan Textile University (No. FZ2020005).

References

  1. Y. Ding and Z. Yang, "Fabric image defect detection based on fission particle filter algorithm," Textile Auxiliaries, vol. 36, no. 4, pp. 60-64, 2019.
  2. S. Zhao, J. Zhang, J. Wang, and C. Xu, "Fabric defect detection algorithm based on two-stage deep transfer learning," Journal of Mechanical Engineering, vol. 57, no. 17, pp. 86-97, 2021. https://doi.org/10.3901/JME.2021.17.086
  3. N. Lang, D. Wang, P. Cheng, S. Zuo, and P. Zhang, "Virtual-sample-based defect detection algorithm for aluminum tube surface," Measurement Science and Technology, vol. 32, no. 8, article no. 085001, 2021. https://doi.org/10.1088/1361-6501/abf865
  4. Q. Xu and L. Zhou, "Straw defect detection algorithm based on pruned YOLOv3," in Proceedings of 2021 4th International Conference on Control and Computer Vision, Macau, China, 2021, pp. 64-69.
  5. H. Y. Ngan, G. K. Pang, and N. H. Yung, "Motif-based defect detection for patterned fabric," Pattern Recognition, vol. 41, no. 6, pp. 1878-1894, 2008. https://doi.org/10.1016/j.patcog.2007.11.014
  6. S. Ma, W. Liu, C. You, S. Jia, and Y. Wu, "An improved defect detection algorithm of jean fabric based on optimized Gabor filter," Journal of Information Processing Systems, vol. 16, no. 5, pp. 1008-1014, 2020. https://doi.org/10.3745/JIPS.02.0140
  7. J. Luo and K. Lu, "Yarn-dyed fabric defect detection based on convolution neural network and transfer learning," Shanghai Textile Science & Technology, vol. 47, no. 6, pp. 52-56, 2019.
  8. C. Li, G. Gao, Z. Liu, Q. Liu, and W. Li, "Fabric defect detection algorithm based on histogram of oriented gradient and low-rank decomposition," Journal of Textile Research, vol. 38, no. 3, pp. 149-154, 2017.
  9. J. Zhou, J. Wang, and W. Gao, "Unsupervised fabric defect segmentation using local texture feature," Journal of Textile Research, vol. 37, no. 12, pp. 43-48, 2016.
  10. D. Yapi, M. S. Allili, and N. Baaziz, "Automatic fabric defect detection using learning-based local textural distributions in the contourlet domain," IEEE Transactions on Automation Science and Engineering, vol. 15, no. 3, pp. 1014-1026, 2018. https://doi.org/10.1109/tase.2017.2696748