Abstract
Fabric defect detection is a crucial step for the fabric production process. However, existing traditional methods of fabric defect detection only pay attention to the simplest plain and twill fabrics, while ignoring the complicated diverse texture fabric. In this paper, we proposed a robust defect detection method based on CenterNet for diverse texture fabric. Firstly, we used ResNet-50 backbone network to extract the fabric image features. Then we applied up-sampling of three-fold deconvolution to obtain the high-resolution feature images. Finally, defects in the diverse texture were located and recognized. Experimental results showed that the proposed method can successfully detect the defects and achieve a high mAP. Compared with the current state-of-the-art methods, such as Faster-RCNN, EffcientDet and Yolo-V4, the proposed method outperforms these methods in terms of accuracy and robustness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jing, J.F.: A coarse-to-fine method for glass fiber fabric surface defect detection. J. Text. Inst. 112(3), 388–397 (2021)
Li, F.: Bag of tricks for fabric defect detection based on Cascade R-CNN. Text. Res. J. 91(5–6), 599–612 (2021)
Zhou, T.: A series of efficient defect detectors for fabric quality inspection. Measurement 172, 108885 (2021)
Li, C., Liu, C., Gao, G., Liu, Z., Wang, Y.: Robust low-rank decomposition of multi-channel feature matrices for fabric defect detection. Multimed. Tools Appl. 78(6), 7321–7339 (2018). https://doi.org/10.1007/s11042-018-6483-6
Pan, R.: Defect detection of printed fabrics using normalized cross correlation. J. Text. Res. 31(12), 134–138 (2010)
Kuo, C.F.: Automatic detection system for printed fabric defects. Text. Res. J. 82(6), 591–601 (2012)
Liu, J.H.: Multistage GAN for fabric defect detection. IEEE Trans. Image Process. 29, 3388–3400 (2019)
Jing, J.F.: Mobile-Unet: an efficient convolutional neural network for fabric defect detection. Text. Res. J. (2020)
Li, M.: Application of Gaussian mixture model on defect detection of print fabric. J. Text. Res. 36(8), 94–98 (2015)
Zhou, X.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)
He, K.M., Zhang, X.Y.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Tan, M., Pang, R.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10778–10787 (2020)
Jing, J.: Fabric defect detection using the improved YOLOv3 model. J. Eng. Fibers Fabr. 15(1), 1–10 (2020)
Bochkovskiy, A.: YOLOv4: optimal speed and accuracy of object detection (2020)
Liu, Z., Guo, Z.: Research on texture defect detection based on faster-RCNN and feature fusion. In: Proceedings of the 11th International Conference on Machine Learning and Computing, Zhuhai, China, 22–23 February 2019, pp. 429–433 (2019)
Liu, S., Ma, H.: Combined attention mechanism and CenterNet pedestrian detection algorithm. In: 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp. 1978–1982 (2021). https://doi.org/10.1109/IAEAC50856.2021.9391037
Acknowledgment
This work was supported by financial support received from the National Natural Science Foundation of China (No. 61902302). Shaanxi Provincial Key R&D Program Project (2021GY-261), Shaanxi Innovation Ability Support Program (2021TD-29).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kong, W., Zhang, H., Jing, J., Shi, M. (2021). A Defect Detection Method for Diverse Texture Fabric Based on CenterNet. In: Huang, DS., Jo, KH., Li, J., Gribova, V., Hussain, A. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science(), vol 12837. Springer, Cham. https://doi.org/10.1007/978-3-030-84529-2_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-84529-2_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84528-5
Online ISBN: 978-3-030-84529-2
eBook Packages: Computer ScienceComputer Science (R0)