TY - JOUR
T1 - Welding defects classification by weakly supervised semantic segmentation
AU - Zhang, Baoxin
AU - Wang, Xiaopeng
AU - Cui, Jinhan
AU - Wu, Juntao
AU - Wang, Xu
AU - Li, Yan
AU - Li, Jinhang
AU - Tan, Yunhua
AU - Chen, Xiaoming
AU - Wu, Wenliang
AU - Yu, Xinghua
N1 - Publisher Copyright:
© 2023
PY - 2023/9
Y1 - 2023/9
N2 - Radiographic non-destructive evaluation (NDE) is an essential technique for understanding defects in welds. These radiographs require certified workers to interpret them to identify the presence of defects. Recent deep learning techniques, primarily semantic segmentation, could help welding defect detection and classification. Using image segmentation technology to obtain performance evaluations of the presence, location, and size of defects can improve the stability of defect evaluations while saving a great deal of time. However, supervised instance segmentation requires many manually implemented pixel-level annotations, dramatically increasing the difficulty and cost of achieving non-destructive evaluations. In our work, the weakly supervised semantic segmentation based on the Cut-Cascade RCNN model is used to classify defects. The cascade RCNN obtains the region of interest (ROI) and classification information. In the ROI, adaptive threshold segmentation of the defects is implemented, and the image is filtered to obtain the mask information. The accuracy of using the Cut-Cascade RCNN model in our x-ray dataset size can reach 90.15%.
AB - Radiographic non-destructive evaluation (NDE) is an essential technique for understanding defects in welds. These radiographs require certified workers to interpret them to identify the presence of defects. Recent deep learning techniques, primarily semantic segmentation, could help welding defect detection and classification. Using image segmentation technology to obtain performance evaluations of the presence, location, and size of defects can improve the stability of defect evaluations while saving a great deal of time. However, supervised instance segmentation requires many manually implemented pixel-level annotations, dramatically increasing the difficulty and cost of achieving non-destructive evaluations. In our work, the weakly supervised semantic segmentation based on the Cut-Cascade RCNN model is used to classify defects. The cascade RCNN obtains the region of interest (ROI) and classification information. In the ROI, adaptive threshold segmentation of the defects is implemented, and the image is filtered to obtain the mask information. The accuracy of using the Cut-Cascade RCNN model in our x-ray dataset size can reach 90.15%.
KW - Deep learning
KW - Non-destructive evaluation
KW - Welding defect
UR - http://www.scopus.com/inward/record.url?scp=85164211853&partnerID=8YFLogxK
U2 - 10.1016/j.ndteint.2023.102899
DO - 10.1016/j.ndteint.2023.102899
M3 - Article
AN - SCOPUS:85164211853
SN - 0963-8695
VL - 138
JO - NDT and E International
JF - NDT and E International
M1 - 102899
ER -