Abstract
For the problem of complex tile surface pattern background, different defect features, low efficiency, and high leakage rate of manual and traditional recognition, this paper proposes a deep learning-based tile surface defect detection method. First, the YOLOv5 backbone network is replaced with a lightweight network ShuffleNetV2, and then, the convolutional block attention module (CBAM) is added. Finally, a lightweight tile detection system is constructed by using CrossEntropyLoss instead of the loss function in the original network. The comparison experiments with six networks such as YOLOv4, Faster RCNN, and SSD show that the algorithm detects tile defects with 95.10% Precision and 92.91% mAP, which is 3.02 percentage points better than the defect recognition accuracy of the network before improvement. It solves the industry-wide problem of long-term reliance on manual visual recognition for tile surface defect detection, realizes automatic and high-precision detection of tile defects, and the resulting tile defect detection technology can be put into stable and reliable operation in the ceramic industry.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Guangya, L., et al.: Research on visual detection method of tile surface defects based on gabor transformation and region growing. Modern Comput. 24, 37–42 (2019)
Huialiang, Z., et al.: Detection of surface defects in ceramic tiles with complex texture. IEEE Access 9, 92788–92797 (2021)
Junhua, L., et al.: Research on defect detection algorithm of ceramic tile surface with multi-feature fusion. Comput. Eng. Appl. 56(15), 191–198 (2020)
Mariyadi, B., et al.: 2D detection model of defect on the surface of ceramic tile by an artificial neural network. J. Phys. Conf. Ser. 1764(1), 012176 (2021)
Zehui, L.: Research on Visual Detection System and Algorithm of Polished Tile Surface Defects. The Guangdong University of Technology, Guangdong (2021)
Taochuan, Z. et al.: Development of an online fast non-destructive testing system for ceramic tiles based on deep learning. Mech. Eng. Autom. 6, 129–130+133 (2020)
Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., Fricout, G.: Steel defect classification with Max-Pooling convolutional neural networks. In: The 2012 International Joint Conference on Neural Networks, IJCNN, pp. 1–6 (2012)
Lin, J., Yao, Y., Ma, L., Wang, Y.: Detection of a casting defect tracked by deep convolution neural network. The International Journal of Advanced Manufacturing Technology 97(1–4), 573–581 (2018). https://doi.org/10.1007/s00170-018-1894-0
Redmon, J., et al.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Redmon, J., et al.: Better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition, p. 6517—652. IEEE, New York (2017)
Redmon, J., et al.: Yolov3: An Incremental Improvement. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)
Bochkovskiy, A., et al.: YOLOv4: Optimal speed and accuracy of object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)
Li, W., et al.: Garbage classification and detection based on YOLOv5s network. Pack. Eng. 42(8), 50–56 (2021)
Fangbo, Z., et al.: Safety helmet detection based on YOLOv5. In: 2021 IEEE International Conference on Power Electronics. Computer Applications (ICPECA), pp. 6–11. IEEE, New York (2021)
Misra, D.: Mish: A self regularized non-monotonic neural activation function (2019)
Yanan, S.: et al.: Rail surface defect detection method based on YOLOv3 deep learning networks. In: 2018 Chinese Automation Congress (CAC), pp. 1563–1568 (2018)
Bo, G.: et al.: Fabric defect detection algorithm based on improved YOLOv5 model. J. Zhejiang Sci-Tech Univ. Nat. Scie. Ed. (2020)
Wenbin, X.: et al.: Real-time static gesture recognition method based on ShuffleNetv2-YOLOv3 model. J. Zhejiang Univ. Eng. Sci. 55(10), 1815–1824+ 1846 (2021)
Yang, Y., et al.: An improved CNN fault diagnosis model fusion depth separable small convolution kernel and CBAM. Electron. Measur. Technol. 45(6), 171–178 (2022)
Yuchun, C., et al.: Research on knowledge distillation algorithm for target detection based on YOLOv4. Comput. Sci. 49(S1), 337–344 (2022)
Bin, Z., Cong, Z.: Dense crowd detection algorithm based on Faster-RCNN. Comput. Appl. 1–7 (2022)
Muqin, L., et al.: Vehicle detection based on SSD-mobilenet V3 model. Sens. Microsyst. 41(6), 142–145 (2022)
Liye, S., et al.: Power grid components and defect identification method based on improved EfficientDet. J. Electrotech. Technol. 37(9), 2241–2251 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Song, L., Xiao, J., Wu, Z., Liu, M., Xiang, Z. (2022). Tile Defect Detection Based on the Improved S2C-YOLOv5. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science(), vol 13604. Springer, Cham. https://doi.org/10.1007/978-3-031-20497-5_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-20497-5_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20496-8
Online ISBN: 978-3-031-20497-5
eBook Packages: Computer ScienceComputer Science (R0)