Fabric Defect Detection Based on Faster RCNN

  • Bing Wei
  • Kuangrong HaoEmail author
  • Xue-song Tang
  • Lihong Ren
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 849)


Considering that the traditional detection of fabric defect can be time-consuming and less-efficient, a modified faster regional-based convolutional network method (Faster RCNN) based on the VGG structure is proposed. In the paper, we improved the Faster RCNN to suit our fabric defect dataset. In order to reduce the influence of input data for Faster RCNN, we expanded the fabric defect data. Meanwhile, by taking the characteristics of the fabric defect images, we reduce the number of anchors in the Faster RCNN. In the process of training the network, VGG16 can extract the feature map through the 13 conv layers in which the activation function is Relu, and four pooling layers. Then, the region proposal network (RPN) generates the foreground anchors and bounding box regression, and then calculates the proposals. Finally, the ROI Pooling layer uses the proposals from the feature maps to extract the proposal feature into the subsequent full connection and softmax network for classification. The experimental results show the capability of fabric defect detection via the modified Faster RCNN model and indicate its effectiveness.


Fabric defect Classification Detection VGG16 Faster RCNN 


  1. 1.
    Zhu, D., Pan, R., Gao, W.: Yarn-dyed fabric defect detection based on autocorrelation function and GLCM. Autex Res. J. 15(3), 226–232 (2015)CrossRefGoogle Scholar
  2. 2.
    Mak, K.L., Peng, P., Yiu, K.F.C.: Fabric defect detection using morphological filters. Image Vis. Comput. 27(10), 1585–1592 (2009)CrossRefGoogle Scholar
  3. 3.
    Zhu, Q., Wu, M., Li, J.: Fabric defect detection via small scale over-compete basis set. Textile Res. J. 84(15), 1634–1649 (2014)CrossRefGoogle Scholar
  4. 4.
    Jia, L., Chen, C., Liang, J.: Fbaric defect inspection based on lattice segmentation and Gabor filtering. Neurocomputing 238, 84–102 (2017)CrossRefGoogle Scholar
  5. 5.
    Hu, G., Wang, Q., Guo, H.: Unsupervised defect detection in textiles based on Fourier analysis and wavelet shrinkage. Appl. Opt. 54(10), 2963–2980 (2015)CrossRefGoogle Scholar
  6. 6.
    Cohen, F.S., Fan, Z., Attali, S.: Automated inspection of textile fabrics using textural models. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 803–808 (1991)CrossRefGoogle Scholar
  7. 7.
    Li, Y., Zhao, W., Pan, J.: Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Trans. Autom. Sci. Eng. 14(2), 1256–1264 (2017)CrossRefGoogle Scholar
  8. 8.
    Kumar, A.: Neural network based detection of local textile defects. Pattern Recogn. 36(7), 1645–1659 (2003)CrossRefGoogle Scholar
  9. 9.
    Huang, C.C., Chen, I.C.: Neural-fuzzy classification for fabric defects. Text. Res. J. 71(3), 220–224 (2001)CrossRefGoogle Scholar
  10. 10.
    Li, W., Cheng, L.: yarn-dyed woven defect characterization and classification using combined features and support vector machine. J. Textile Inst. Proc. Abstr. 105(2), 163–174 (2014)CrossRefGoogle Scholar
  11. 11.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In arXiv: 1409.1556, Sept 2014Google Scholar
  12. 12.
    Yann, L., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  13. 13.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142–158, JanuaryGoogle Scholar
  14. 14.
    Girshick, R.: Fast R-CNN. IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)Google Scholar
  15. 15.
    Ren, S., He, K., Girchick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)CrossRefGoogle Scholar
  16. 16.
    Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer vision and Pattern Recognition, pp. 2874–2883 (2016)Google Scholar
  17. 17.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanoucke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
  18. 18.
    Liu, Z., Yan, L., Li, C.: Fabric defect detection based on sparse representation of main local binary pattern. Int. J. Cloth. Sci. Technol. 29(3), 282–293 (2017)CrossRefGoogle Scholar
  19. 19.
    Tong, L., Wong, W.K., Kwong, C.K.: Differential evolution-based optimal Gabor filter model for fabric inspection. vol. 173, pp. 1386–1401, January, 2016Google Scholar
  20. 20.
    Tong, L., Wong, W.K., Kwong, C.K.: Fabric defect detection for apparel industry: a nonlocal sparse representation approach. IEEE Access 5, 5947–5964 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Bing Wei
    • 1
  • Kuangrong Hao
    • 1
    Email author
  • Xue-song Tang
    • 1
  • Lihong Ren
    • 1
  1. 1.Engineering Research Center of Digitized Textile and Apparel Technology, Ministry of Education, College of Information Sciences and TechnologyDonghua UniversityShanghaiPeople’s Republic of China

Personalised recommendations