A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection
Defects on fabric surfaces are difficult to identify owing to unsuitable computing devices, highly complex algorithms, small size, and high degree of integration with the fabric. To this end, this study proposes a lightweight fabric defect-detection network, YOLO-SCD, based on attention mechanism. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10091552/ |
| _version_ | 1797849304061181952 |
|---|---|
| author | Xin Luo Qing Ni Ran Tao Youqun Shi |
| author_facet | Xin Luo Qing Ni Ran Tao Youqun Shi |
| author_sort | Xin Luo |
| collection | DOAJ |
| description | Defects on fabric surfaces are difficult to identify owing to unsuitable computing devices, highly complex algorithms, small size, and high degree of integration with the fabric. To this end, this study proposes a lightweight fabric defect-detection network, YOLO-SCD, based on attention mechanism. The introduction of depth-wise separable convolution and the attention mechanism enhanced the capacity of the neck network to extract the defective features and increased the detection speed of the overall network. The extensive experimental results revealed that YOLO-SCD achieved an average accuracy of 82.92%, effective improvement of 8.49% in mAP, and an improvement of 37 fps compared to the original YOLOv4 on a standard fabric defect dataset. By leveraging its swift detection speed and high efficiency, YOLO-SCD excels in both the general fabric defect category and the difficult-to-detect fabric. Overall, it exhibited strong performance in detecting both minor flaws and flaws with high fabric integration. Furthermore, the proposed model was extended to steel datasets with similar characteristics. |
| first_indexed | 2024-04-09T18:42:49Z |
| format | Article |
| id | doaj.art-5e7baa83867a4a6e9c32353da6465f6b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T18:42:49Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5e7baa83867a4a6e9c32353da6465f6b2023-04-10T23:00:48ZengIEEEIEEE Access2169-35362023-01-0111335543356910.1109/ACCESS.2023.326426210091552A Lightweight Detector Based on Attention Mechanism for Fabric Defect DetectionXin Luo0https://orcid.org/0000-0002-4448-8971Qing Ni1https://orcid.org/0000-0003-4185-3440Ran Tao2https://orcid.org/0000-0002-7343-6388Youqun Shi3School of Computer Science and Technology, Donghua University, Shanghai, ChinaSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaDefects on fabric surfaces are difficult to identify owing to unsuitable computing devices, highly complex algorithms, small size, and high degree of integration with the fabric. To this end, this study proposes a lightweight fabric defect-detection network, YOLO-SCD, based on attention mechanism. The introduction of depth-wise separable convolution and the attention mechanism enhanced the capacity of the neck network to extract the defective features and increased the detection speed of the overall network. The extensive experimental results revealed that YOLO-SCD achieved an average accuracy of 82.92%, effective improvement of 8.49% in mAP, and an improvement of 37 fps compared to the original YOLOv4 on a standard fabric defect dataset. By leveraging its swift detection speed and high efficiency, YOLO-SCD excels in both the general fabric defect category and the difficult-to-detect fabric. Overall, it exhibited strong performance in detecting both minor flaws and flaws with high fabric integration. Furthermore, the proposed model was extended to steel datasets with similar characteristics.https://ieeexplore.ieee.org/document/10091552/Fabric defect detectionSoftPoolattention mechanismdepthwise separable convolutionlightweight |
| spellingShingle | Xin Luo Qing Ni Ran Tao Youqun Shi A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection IEEE Access Fabric defect detection SoftPool attention mechanism depthwise separable convolution lightweight |
| title | A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection |
| title_full | A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection |
| title_fullStr | A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection |
| title_full_unstemmed | A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection |
| title_short | A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection |
| title_sort | lightweight detector based on attention mechanism for fabric defect detection |
| topic | Fabric defect detection SoftPool attention mechanism depthwise separable convolution lightweight |
| url | https://ieeexplore.ieee.org/document/10091552/ |
| work_keys_str_mv | AT xinluo alightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT qingni alightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT rantao alightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT youqunshi alightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT xinluo lightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT qingni lightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT rantao lightweightdetectorbasedonattentionmechanismforfabricdefectdetection AT youqunshi lightweightdetectorbasedonattentionmechanismforfabricdefectdetection |