Fabric Surface Defect Detection Using SE-SSDNet
For fabric defect detection, the crucial issue is that large defects can be detected but not small ones, and vice versa, and this symmetric contradiction cannot be solved by a single method, especially for colored fabrics. In this paper, we propose a method based on a combination of two networks, SE...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/11/2373 |
| _version_ | 1797466415101378560 |
|---|---|
| author | Hanqing Zhao Tuanshan Zhang |
| author_facet | Hanqing Zhao Tuanshan Zhang |
| author_sort | Hanqing Zhao |
| collection | DOAJ |
| description | For fabric defect detection, the crucial issue is that large defects can be detected but not small ones, and vice versa, and this symmetric contradiction cannot be solved by a single method, especially for colored fabrics. In this paper, we propose a method based on a combination of two networks, SE and SSD, namely the SE-SSD Net method. The model is based on the SSD network and adds the SE module for squeezing and the Excitation module after its convolution operation, which is used to increase the weight of the model for the feature channels containing defect information while re-preserving the original network to extract feature maps of different scales for detection. The global features are then subjected to the Excitation operation to obtain the weights of different channels, which are multiplied by the original features to form the final features so that the model can pay more attention to the channel features with a large amount of information. In this way, large-scale feature maps can be used to detect small defects, while small-scale feature maps are used to detect relatively large defects, thus solving the asymmetry problem in detection. The experimental results show that our proposed algorithm can detect six different defects in colored fabrics, which basically meets the practical needs. |
| first_indexed | 2024-03-09T18:35:40Z |
| format | Article |
| id | doaj.art-d3114ec34fd04430872b010eb7e41f71 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T18:35:40Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-d3114ec34fd04430872b010eb7e41f712023-11-24T07:09:18ZengMDPI AGSymmetry2073-89942022-11-011411237310.3390/sym14112373Fabric Surface Defect Detection Using SE-SSDNetHanqing Zhao0Tuanshan Zhang1Department of Materials Science and Engineering, Northwestern Polytechnical University, Xi’an 710072, ChinaMechanical and Electrical Engineering Department, Xi’an Polytechnic University, Xi’an 710048, ChinaFor fabric defect detection, the crucial issue is that large defects can be detected but not small ones, and vice versa, and this symmetric contradiction cannot be solved by a single method, especially for colored fabrics. In this paper, we propose a method based on a combination of two networks, SE and SSD, namely the SE-SSD Net method. The model is based on the SSD network and adds the SE module for squeezing and the Excitation module after its convolution operation, which is used to increase the weight of the model for the feature channels containing defect information while re-preserving the original network to extract feature maps of different scales for detection. The global features are then subjected to the Excitation operation to obtain the weights of different channels, which are multiplied by the original features to form the final features so that the model can pay more attention to the channel features with a large amount of information. In this way, large-scale feature maps can be used to detect small defects, while small-scale feature maps are used to detect relatively large defects, thus solving the asymmetry problem in detection. The experimental results show that our proposed algorithm can detect six different defects in colored fabrics, which basically meets the practical needs.https://www.mdpi.com/2073-8994/14/11/2373fabric defectSSDdefect detectionchannel weight distributionSE-SSDsymmetrical contradiction |
| spellingShingle | Hanqing Zhao Tuanshan Zhang Fabric Surface Defect Detection Using SE-SSDNet Symmetry fabric defect SSD defect detection channel weight distribution SE-SSD symmetrical contradiction |
| title | Fabric Surface Defect Detection Using SE-SSDNet |
| title_full | Fabric Surface Defect Detection Using SE-SSDNet |
| title_fullStr | Fabric Surface Defect Detection Using SE-SSDNet |
| title_full_unstemmed | Fabric Surface Defect Detection Using SE-SSDNet |
| title_short | Fabric Surface Defect Detection Using SE-SSDNet |
| title_sort | fabric surface defect detection using se ssdnet |
| topic | fabric defect SSD defect detection channel weight distribution SE-SSD symmetrical contradiction |
| url | https://www.mdpi.com/2073-8994/14/11/2373 |
| work_keys_str_mv | AT hanqingzhao fabricsurfacedefectdetectionusingsessdnet AT tuanshanzhang fabricsurfacedefectdetectionusingsessdnet |