TY - GEN
T1 - Multi-defect detection for magnetic tile based on SE-U-Net
AU - Cao, Xincheng
AU - Yao, Bin
AU - Chen, Binqiang
AU - Wang, Yu
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/6
Y1 - 2020/11/6
N2 - Vision-based on-line full detection of surface defects is of great significance to the production efficiency and quality of magnetic tiles. In this work, we introduce a pixel-wise surface defect detection model called SE-U-Net, which simultaneously realizes detection and classification. The image augmentation based on instance transfer effectively reduces the imbalance between the background and the defect. The squeeze-and-excitation module empowers U-Net to adaptively learn the shallow information matched with deep features in the skip path, enhancing the ability to identify small defects with a few of additional network parameters. Experiments show that the recognition accuracy of this model exceeds the existing methods, and the mean pixel-accuracy reaches 0.97.
AB - Vision-based on-line full detection of surface defects is of great significance to the production efficiency and quality of magnetic tiles. In this work, we introduce a pixel-wise surface defect detection model called SE-U-Net, which simultaneously realizes detection and classification. The image augmentation based on instance transfer effectively reduces the imbalance between the background and the defect. The squeeze-and-excitation module empowers U-Net to adaptively learn the shallow information matched with deep features in the skip path, enhancing the ability to identify small defects with a few of additional network parameters. Experiments show that the recognition accuracy of this model exceeds the existing methods, and the mean pixel-accuracy reaches 0.97.
KW - Convolutional networks
KW - Deep learning
KW - Magnetic tile
KW - Multi-defect detection
KW - Semantic Segmentation
UR - https://www.scopus.com/pages/publications/85100679704
U2 - 10.1109/ISPCE-CN51288.2020.9321855
DO - 10.1109/ISPCE-CN51288.2020.9321855
M3 - 会议稿件
AN - SCOPUS:85100679704
T3 - ISPCE-CN 2020 - IEEE International Symposium on Product Compliance Engineering-Asia 2020
BT - ISPCE-CN 2020 - IEEE International Symposium on Product Compliance Engineering-Asia 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Symposium on Product Compliance Engineering-Asia, ISPCE-CN 2020
Y2 - 6 November 2020 through 8 November 2020
ER -