A high-precision segmentation network for industrial surface defect detection
Accurate surface defect detection is essential for improving product quality and reducing manufacturing costs, particularly in high-precision industries. However, existing deep learning methods struggle with multi-scale feature fusion and spatial information preservation. To address these challenges...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-05-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0274903 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850249580868796416 |
|---|---|
| author | Hao Chen Byung-Won Min |
| author_facet | Hao Chen Byung-Won Min |
| author_sort | Hao Chen |
| collection | DOAJ |
| description | Accurate surface defect detection is essential for improving product quality and reducing manufacturing costs, particularly in high-precision industries. However, existing deep learning methods struggle with multi-scale feature fusion and spatial information preservation. To address these challenges, this paper proposes the Spatial-Positional and Cross-Scale Fusion Network (SPCS-Net), an advanced segmentation network incorporating the Spatial-Positional Attention Module (SPAM) and the Cross-Scale Attention Fusion Module (CSAFM). SPAM integrates multi-scale convolutions, spatial attention mechanisms, and positional encoding to enhance the perception of defects with varying shapes. This design helps mitigate spatial information loss commonly observed in traditional U-Net models. CSAFM optimizes multi-scale feature fusion in the decoding stage by employing asymmetric convolutions and an adaptive feature weighting mechanism, effectively bridging the gap between high-level semantic information and low-level spatial details. Experimental results demonstrate that SPCS-Net outperforms state-of-the-art models on the NEU-Seg, MBP-Seg, and USB-Seg datasets, achieving F1 scores of 0.8854, 0.6543, and 0.7793, respectively, with Mean Intersection over Union scores of 0.7964, 0.5654, and 0.6674. Furthermore, SPCS-Net attains an inference speed of 104 f/s on MBP-Seg, striking a balance between accuracy and efficiency. These results highlight SPCS-Net as a promising solution for surface defect segmentation, with potential applications in automated quality inspection and material science. |
| format | Article |
| id | doaj-art-933ccbafe37540a6a805cfea2ae31a05 |
| institution | OA Journals |
| issn | 2158-3226 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj-art-933ccbafe37540a6a805cfea2ae31a052025-08-20T01:58:28ZengAIP Publishing LLCAIP Advances2158-32262025-05-01155055118055118-1110.1063/5.0274903A high-precision segmentation network for industrial surface defect detectionHao Chen0Byung-Won Min1School of Information Engineering, Nantong Institute of Technology, Nantong, Jiangsu, ChinaDivision of Information and Communication Convergence Engineering, Mokwon University, Daejeon, South KoreaAccurate surface defect detection is essential for improving product quality and reducing manufacturing costs, particularly in high-precision industries. However, existing deep learning methods struggle with multi-scale feature fusion and spatial information preservation. To address these challenges, this paper proposes the Spatial-Positional and Cross-Scale Fusion Network (SPCS-Net), an advanced segmentation network incorporating the Spatial-Positional Attention Module (SPAM) and the Cross-Scale Attention Fusion Module (CSAFM). SPAM integrates multi-scale convolutions, spatial attention mechanisms, and positional encoding to enhance the perception of defects with varying shapes. This design helps mitigate spatial information loss commonly observed in traditional U-Net models. CSAFM optimizes multi-scale feature fusion in the decoding stage by employing asymmetric convolutions and an adaptive feature weighting mechanism, effectively bridging the gap between high-level semantic information and low-level spatial details. Experimental results demonstrate that SPCS-Net outperforms state-of-the-art models on the NEU-Seg, MBP-Seg, and USB-Seg datasets, achieving F1 scores of 0.8854, 0.6543, and 0.7793, respectively, with Mean Intersection over Union scores of 0.7964, 0.5654, and 0.6674. Furthermore, SPCS-Net attains an inference speed of 104 f/s on MBP-Seg, striking a balance between accuracy and efficiency. These results highlight SPCS-Net as a promising solution for surface defect segmentation, with potential applications in automated quality inspection and material science.http://dx.doi.org/10.1063/5.0274903 |
| spellingShingle | Hao Chen Byung-Won Min A high-precision segmentation network for industrial surface defect detection AIP Advances |
| title | A high-precision segmentation network for industrial surface defect detection |
| title_full | A high-precision segmentation network for industrial surface defect detection |
| title_fullStr | A high-precision segmentation network for industrial surface defect detection |
| title_full_unstemmed | A high-precision segmentation network for industrial surface defect detection |
| title_short | A high-precision segmentation network for industrial surface defect detection |
| title_sort | high precision segmentation network for industrial surface defect detection |
| url | http://dx.doi.org/10.1063/5.0274903 |
| work_keys_str_mv | AT haochen ahighprecisionsegmentationnetworkforindustrialsurfacedefectdetection AT byungwonmin ahighprecisionsegmentationnetworkforindustrialsurfacedefectdetection AT haochen highprecisionsegmentationnetworkforindustrialsurfacedefectdetection AT byungwonmin highprecisionsegmentationnetworkforindustrialsurfacedefectdetection |