YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect
Welding processes significantly impact product quality as a crucial part of industrial production. Due to the reflection, diversity, complexity, and minuteness of solder defects, traditional detection methods struggle to detect surface defects in solder points effectively. Although object detection...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10749805/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846163826668470272 |
|---|---|
| author | Xinyao Wang Yubo Xuan Xuetong Huang Qianhua Yan |
| author_facet | Xinyao Wang Yubo Xuan Xuetong Huang Qianhua Yan |
| author_sort | Xinyao Wang |
| collection | DOAJ |
| description | Welding processes significantly impact product quality as a crucial part of industrial production. Due to the reflection, diversity, complexity, and minuteness of solder defects, traditional detection methods struggle to detect surface defects in solder points effectively. Although object detection based on deep learning has made significant advances, detecting smaller objects remains challenging. To address these issues, we propose an improved defect detection network based on YOLOv9, named attention flexible kernel YOLO (YOLO-AFK). In particular, we propose a fusion attention network (FANet) that can enhance the model’s ability to detect small defects by adaptively adjusting the receptive field of targets during feature extraction. Meanwhile, we use the alterable kernel convolution (AKConv), a variable kernel convolution, that breaks away from traditional convolutions limited to fixed local windows and sampling shapes. It can flexibly adjust the size and shape of the convolution kernels according to the solder targets, leading to more efficient feature extraction, thus achieving a lighter network. To gather more contextual and high-resolution information and enhance the detection accuracy and generalization ability for small objects and low-contrast targets, the cross-stage partial network fusion (C2f) module is designed to fuse feature maps from different levels. We evaluated the model using the publicly available NEU dataset and our proprietary solder point dataset, the fine-grain solder defect dataset (FG-SDD). Compared to previous studies, YOLO-AFK outperforms other state-of-the-art networks in terms of mean Average Precision (mAP) and Precision, with the parameter count increasing by only 12.4M, Precision improving by 10.1%, mAP increasing by 5.6%, and FPS improving by 23%. These results demonstrate the superior performance of the proposed network in detecting defects with complex structures. In particular, for industrial solder joint defect detection, YOLO-AFK not only improves detection accuracy but also significantly enhances the recognition of small targets and complex solder joint defects, showcasing the network’s substantial potential and practical value in real-world production environments. The code is available at: <uri>https://github.com/Lwsk-wxy/yolo_afk.git</uri>. |
| format | Article |
| id | doaj-art-3c3447935a8a42cd8f51b61534eb71fa |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3c3447935a8a42cd8f51b61534eb71fa2024-11-19T00:01:38ZengIEEEIEEE Access2169-35362024-01-011216623816625210.1109/ACCESS.2024.349554010749805YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints DefectXinyao Wang0https://orcid.org/0009-0009-4995-4642Yubo Xuan1https://orcid.org/0000-0002-7781-7874Xuetong Huang2Qianhua Yan3https://orcid.org/0009-0006-4552-386XCollege of Communication Engineering, Jilin University, Changchun, ChinaCollege of Communication Engineering, Jilin University, Changchun, ChinaCollege of Communication Engineering, Jilin University, Changchun, ChinaCollege of Communication Engineering, Jilin University, Changchun, ChinaWelding processes significantly impact product quality as a crucial part of industrial production. Due to the reflection, diversity, complexity, and minuteness of solder defects, traditional detection methods struggle to detect surface defects in solder points effectively. Although object detection based on deep learning has made significant advances, detecting smaller objects remains challenging. To address these issues, we propose an improved defect detection network based on YOLOv9, named attention flexible kernel YOLO (YOLO-AFK). In particular, we propose a fusion attention network (FANet) that can enhance the model’s ability to detect small defects by adaptively adjusting the receptive field of targets during feature extraction. Meanwhile, we use the alterable kernel convolution (AKConv), a variable kernel convolution, that breaks away from traditional convolutions limited to fixed local windows and sampling shapes. It can flexibly adjust the size and shape of the convolution kernels according to the solder targets, leading to more efficient feature extraction, thus achieving a lighter network. To gather more contextual and high-resolution information and enhance the detection accuracy and generalization ability for small objects and low-contrast targets, the cross-stage partial network fusion (C2f) module is designed to fuse feature maps from different levels. We evaluated the model using the publicly available NEU dataset and our proprietary solder point dataset, the fine-grain solder defect dataset (FG-SDD). Compared to previous studies, YOLO-AFK outperforms other state-of-the-art networks in terms of mean Average Precision (mAP) and Precision, with the parameter count increasing by only 12.4M, Precision improving by 10.1%, mAP increasing by 5.6%, and FPS improving by 23%. These results demonstrate the superior performance of the proposed network in detecting defects with complex structures. In particular, for industrial solder joint defect detection, YOLO-AFK not only improves detection accuracy but also significantly enhances the recognition of small targets and complex solder joint defects, showcasing the network’s substantial potential and practical value in real-world production environments. The code is available at: <uri>https://github.com/Lwsk-wxy/yolo_afk.git</uri>.https://ieeexplore.ieee.org/document/10749805/Deep learningcomplex feature extractionsolder defect detectionobject detection |
| spellingShingle | Xinyao Wang Yubo Xuan Xuetong Huang Qianhua Yan YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect IEEE Access Deep learning complex feature extraction solder defect detection object detection |
| title | YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect |
| title_full | YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect |
| title_fullStr | YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect |
| title_full_unstemmed | YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect |
| title_short | YOLO-AFK: Advanced Fine-Grained Object Detection for Complex Solder Joints Defect |
| title_sort | yolo afk advanced fine grained object detection for complex solder joints defect |
| topic | Deep learning complex feature extraction solder defect detection object detection |
| url | https://ieeexplore.ieee.org/document/10749805/ |
| work_keys_str_mv | AT xinyaowang yoloafkadvancedfinegrainedobjectdetectionforcomplexsolderjointsdefect AT yuboxuan yoloafkadvancedfinegrainedobjectdetectionforcomplexsolderjointsdefect AT xuetonghuang yoloafkadvancedfinegrainedobjectdetectionforcomplexsolderjointsdefect AT qianhuayan yoloafkadvancedfinegrainedobjectdetectionforcomplexsolderjointsdefect |