FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.

Aiming at the current problems in the field of industrial defect segmentation, such as difficulty of obtaining a large number of defect samples, low recognition accuracy and lack of segmentation accuracy, a surface defect segmentation model for aluminum based on feature differentiation is proposed:...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingzhu Tang, Wencheng Wang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0320060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261501710958592
author Mingzhu Tang
Wencheng Wang
author_facet Mingzhu Tang
Wencheng Wang
author_sort Mingzhu Tang
collection DOAJ
description Aiming at the current problems in the field of industrial defect segmentation, such as difficulty of obtaining a large number of defect samples, low recognition accuracy and lack of segmentation accuracy, a surface defect segmentation model for aluminum based on feature differentiation is proposed: FDTransUnet. First, the limited defective samples are effectively expanded by the feature differentiation data augmentation strategy to alleviate the overfitting problem caused by the insufficient sample. Second, the Transformer architecture is added by improving the U-net network, and the improved network combines the global self-attention mechanism of the Transformer and the hierarchical structure of the U-net, which can effectively extract the local and global information in the defect sample. Finally, a composite loss function is constructed to address the problem of unbalanced foreground and background sizes of defective samples and to improve segmentation accuracy. The experimental results show that FDTransUnet achieves 94.5% MPA and 89.7% Dice coefficient on the aluminum surface defect dataset. In the final generalization experiment, FDTransUnet is validated with other mainstream segmentation models on the steel surface defect dataset, and the experiment proves that the segmentation model has good generalization performance and robustness, and can be applied to different scenarios of industrial inspection.
format Article
id doaj-art-c80f4ab0f5c042eeb2159ba10193aca6
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-c80f4ab0f5c042eeb2159ba10193aca62025-08-20T01:55:22ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e032006010.1371/journal.pone.0320060FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.Mingzhu TangWencheng WangAiming at the current problems in the field of industrial defect segmentation, such as difficulty of obtaining a large number of defect samples, low recognition accuracy and lack of segmentation accuracy, a surface defect segmentation model for aluminum based on feature differentiation is proposed: FDTransUnet. First, the limited defective samples are effectively expanded by the feature differentiation data augmentation strategy to alleviate the overfitting problem caused by the insufficient sample. Second, the Transformer architecture is added by improving the U-net network, and the improved network combines the global self-attention mechanism of the Transformer and the hierarchical structure of the U-net, which can effectively extract the local and global information in the defect sample. Finally, a composite loss function is constructed to address the problem of unbalanced foreground and background sizes of defective samples and to improve segmentation accuracy. The experimental results show that FDTransUnet achieves 94.5% MPA and 89.7% Dice coefficient on the aluminum surface defect dataset. In the final generalization experiment, FDTransUnet is validated with other mainstream segmentation models on the steel surface defect dataset, and the experiment proves that the segmentation model has good generalization performance and robustness, and can be applied to different scenarios of industrial inspection.https://doi.org/10.1371/journal.pone.0320060
spellingShingle Mingzhu Tang
Wencheng Wang
FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
PLoS ONE
title FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
title_full FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
title_fullStr FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
title_full_unstemmed FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
title_short FDTransUnet: An aluminum surface defect segmentation model based on feature differentiation.
title_sort fdtransunet an aluminum surface defect segmentation model based on feature differentiation
url https://doi.org/10.1371/journal.pone.0320060
work_keys_str_mv AT mingzhutang fdtransunetanaluminumsurfacedefectsegmentationmodelbasedonfeaturedifferentiation
AT wenchengwang fdtransunetanaluminumsurfacedefectsegmentationmodelbasedonfeaturedifferentiation