Affiliations: [a]
School of Electrical and Elctronic Engineering, Hubei University of Technology, Hubei, China
| [b]
College of Artificial Intelligence, Tianjin University of Science & Technology, Tianjin, China
Correspondence:
[*]
Corresponding author. Gaihua Wang, College of Artificial Intelligence,Tianjin University of Science & Technology, 300457, Tianjin, China. E-mail: cirenlamu@tust.edu.cn.
Abstract: The detection of magnetic tile quality is an essential link before the assembly of permanent magnet motor. In order to meet the high standard of magnetic tile surface defect detection and realize the rapid and automatic segmentation of magnetic tile defects, a magnetic tile surface defect segmentation algorithm based on cross self-attention model (CSAM) is proposed. It adopts high-low level semantic feature fusion method to build the dependency relationship between the deep and shallow features. Multiple auxiliary loss functions are used to constrain the network and reduce the noise in the deep features. In addition, an image enhancement method is also designed to solve the problem of insufficient annotated data. The experimental results show that the network can achieve 79.6% mIoU and 98.5% PA, which can meet the high standard requirements of magnetic tile manufacturing.
