A lightweight model for digital printing fabric defect detection based on YOLOX
Online detection of digital printing defects is a necessary but challenging topic. The performance of the current detection methods is still not ideal for the diversified patterns of digital printing fabric defects and the realtime requirements of online detection. In this paper, we proposed a light...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-10-01
|
| Series: | Journal of Engineered Fibers and Fabrics |
| Online Access: | https://doi.org/10.1177/15589250231208702 |
| _version_ | 1827777682888196096 |
|---|---|
| author | Zebin Su Hao Zhang Pengfei Li Huanhuan Zhang Yanjun Lu |
| author_facet | Zebin Su Hao Zhang Pengfei Li Huanhuan Zhang Yanjun Lu |
| author_sort | Zebin Su |
| collection | DOAJ |
| description | Online detection of digital printing defects is a necessary but challenging topic. The performance of the current detection methods is still not ideal for the diversified patterns of digital printing fabric defects and the realtime requirements of online detection. In this paper, we proposed a lightweight model of digital printing fabric defect detection based on YOLOX. Firstly, according to the characteristics of many types of defects and complex background of digitally printed fabrics, a defect detection network structure based on YOLOX is constructed. Then, the SE attention module is introduced to enhance important features and weaken unimportant features, which make the extracted features more directional. And it can further solve the influence of small feature size on the detection accuracy of small targets. The experimental results show that the proposed model has a detection accuracy of 66.2 mAP on our self-built dataset, which is 2.7 percentage points higher than YOLOX. This method can effectively solve the problem that low detection accuracy of small defects. The proposed model can meet the real-time requirements and improve the detection accuracy of small target defects. |
| first_indexed | 2024-03-11T14:21:46Z |
| format | Article |
| id | doaj.art-e2fb4f6369ab451d8f1dc25185c82c74 |
| institution | Directory Open Access Journal |
| issn | 1558-9250 |
| language | English |
| last_indexed | 2024-03-11T14:21:46Z |
| publishDate | 2023-10-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Journal of Engineered Fibers and Fabrics |
| spelling | doaj.art-e2fb4f6369ab451d8f1dc25185c82c742023-10-31T16:03:50ZengSAGE PublishingJournal of Engineered Fibers and Fabrics1558-92502023-10-011810.1177/15589250231208702A lightweight model for digital printing fabric defect detection based on YOLOXZebin Su0Hao Zhang1Pengfei Li2Huanhuan Zhang3Yanjun Lu4Shaanxi Artificial Intelligence Joint Laboratory, Xi’an Polytechnic University, Xi’an, ChinaShaanxi Artificial Intelligence Joint Laboratory, Xi’an Polytechnic University, Xi’an, ChinaSchool of Electronics and Information, Xi’an Polytechnic University, Xi’an, ChinaSchool of Electronics and Information, Xi’an Polytechnic University, Xi’an, ChinaSchool of Mechanical and Instrumental Engineering, Xi’an University of Technology, Xi’an, ChinaOnline detection of digital printing defects is a necessary but challenging topic. The performance of the current detection methods is still not ideal for the diversified patterns of digital printing fabric defects and the realtime requirements of online detection. In this paper, we proposed a lightweight model of digital printing fabric defect detection based on YOLOX. Firstly, according to the characteristics of many types of defects and complex background of digitally printed fabrics, a defect detection network structure based on YOLOX is constructed. Then, the SE attention module is introduced to enhance important features and weaken unimportant features, which make the extracted features more directional. And it can further solve the influence of small feature size on the detection accuracy of small targets. The experimental results show that the proposed model has a detection accuracy of 66.2 mAP on our self-built dataset, which is 2.7 percentage points higher than YOLOX. This method can effectively solve the problem that low detection accuracy of small defects. The proposed model can meet the real-time requirements and improve the detection accuracy of small target defects.https://doi.org/10.1177/15589250231208702 |
| spellingShingle | Zebin Su Hao Zhang Pengfei Li Huanhuan Zhang Yanjun Lu A lightweight model for digital printing fabric defect detection based on YOLOX Journal of Engineered Fibers and Fabrics |
| title | A lightweight model for digital printing fabric defect detection based on YOLOX |
| title_full | A lightweight model for digital printing fabric defect detection based on YOLOX |
| title_fullStr | A lightweight model for digital printing fabric defect detection based on YOLOX |
| title_full_unstemmed | A lightweight model for digital printing fabric defect detection based on YOLOX |
| title_short | A lightweight model for digital printing fabric defect detection based on YOLOX |
| title_sort | lightweight model for digital printing fabric defect detection based on yolox |
| url | https://doi.org/10.1177/15589250231208702 |
| work_keys_str_mv | AT zebinsu alightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT haozhang alightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT pengfeili alightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT huanhuanzhang alightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT yanjunlu alightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT zebinsu lightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT haozhang lightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT pengfeili lightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT huanhuanzhang lightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox AT yanjunlu lightweightmodelfordigitalprintingfabricdefectdetectionbasedonyolox |