DVCW-YOLO for Printed Circuit Board Surface Defect Detection
The accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. However, current approaches to PCB defect detection face challenges, including large model sizes and difficulties in balancing detection accuracy with...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/327 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549415070826496 |
|---|---|
| author | Pei Shi Yuyang Zhang Yunqin Cao Jiadong Sun Deji Chen Liang Kuang |
| author_facet | Pei Shi Yuyang Zhang Yunqin Cao Jiadong Sun Deji Chen Liang Kuang |
| author_sort | Pei Shi |
| collection | DOAJ |
| description | The accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. However, current approaches to PCB defect detection face challenges, including large model sizes and difficulties in balancing detection accuracy with speed. To address these challenges, this paper proposes a novel PCB surface defect detection algorithm, named DVCW-YOLO. First, all standard convolutions in the backbone and neck networks of YOLOv8n are replaced with lightweight DWConv convolutions. In addition, a self-designed C2fCBAM module is introduced to the backbone network for extracting features. Next, within the neck structure, the C2f module is substituted with the more lightweight VOVGSCSP module, thereby reducing model redundancy, simplifying model complexity, and enhancing detection speed. By enhancing prominent features and suppressing less important ones, this modification allows the model to better focus on key regions, thereby improving feature representation capabilities. Finally, the WIoU loss function is implemented to replace the traditional CIoU function in YOLOv8n. This adjustment addresses issues related to low generalization and poor detection performance for small objects or complex backgrounds, while also mitigating the impact of low-quality or extreme samples on model accuracy. Experimental results demonstrate that the DVCW-YOLO model achieves a mean average precision (mAP) of 99.3% and a detection speed of 43.3 frames per second (FPS), which represent improvements of 4% and 4.08%, respectively, over the YOLOv8n model. These results confirm that the proposed model meets the real-time PCB defect detection requirements of small and medium-sized enterprises. |
| format | Article |
| id | doaj-art-b578703139bb4f509ce4522f404f2da7 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-b578703139bb4f509ce4522f404f2da72025-01-10T13:15:11ZengMDPI AGApplied Sciences2076-34172024-12-0115132710.3390/app15010327DVCW-YOLO for Printed Circuit Board Surface Defect DetectionPei Shi0Yuyang Zhang1Yunqin Cao2Jiadong Sun3Deji Chen4Liang Kuang5School of IoT Engineering, Wuxi University, Wuxi 214105, ChinaSchool of IoT Engineering, Wuxi University, Wuxi 214105, ChinaSchool of IoT Engineering, Wuxi University, Wuxi 214105, ChinaSchool of IoT Engineering, Wuxi University, Wuxi 214105, ChinaJiangsu Internet of Things Hyper-Converged Application and Security Engineering Research Center, Wuxi 214105, ChinaSchool of Internet of Things Engineering, Jiangsu Vocational College of Information Technology, Wuxi 214153, ChinaThe accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. However, current approaches to PCB defect detection face challenges, including large model sizes and difficulties in balancing detection accuracy with speed. To address these challenges, this paper proposes a novel PCB surface defect detection algorithm, named DVCW-YOLO. First, all standard convolutions in the backbone and neck networks of YOLOv8n are replaced with lightweight DWConv convolutions. In addition, a self-designed C2fCBAM module is introduced to the backbone network for extracting features. Next, within the neck structure, the C2f module is substituted with the more lightweight VOVGSCSP module, thereby reducing model redundancy, simplifying model complexity, and enhancing detection speed. By enhancing prominent features and suppressing less important ones, this modification allows the model to better focus on key regions, thereby improving feature representation capabilities. Finally, the WIoU loss function is implemented to replace the traditional CIoU function in YOLOv8n. This adjustment addresses issues related to low generalization and poor detection performance for small objects or complex backgrounds, while also mitigating the impact of low-quality or extreme samples on model accuracy. Experimental results demonstrate that the DVCW-YOLO model achieves a mean average precision (mAP) of 99.3% and a detection speed of 43.3 frames per second (FPS), which represent improvements of 4% and 4.08%, respectively, over the YOLOv8n model. These results confirm that the proposed model meets the real-time PCB defect detection requirements of small and medium-sized enterprises.https://www.mdpi.com/2076-3417/15/1/327PCB board defect detectionYOLOv8n modelDVCW-YOLO modelC2fCBAM structureWIoU loss function |
| spellingShingle | Pei Shi Yuyang Zhang Yunqin Cao Jiadong Sun Deji Chen Liang Kuang DVCW-YOLO for Printed Circuit Board Surface Defect Detection Applied Sciences PCB board defect detection YOLOv8n model DVCW-YOLO model C2fCBAM structure WIoU loss function |
| title | DVCW-YOLO for Printed Circuit Board Surface Defect Detection |
| title_full | DVCW-YOLO for Printed Circuit Board Surface Defect Detection |
| title_fullStr | DVCW-YOLO for Printed Circuit Board Surface Defect Detection |
| title_full_unstemmed | DVCW-YOLO for Printed Circuit Board Surface Defect Detection |
| title_short | DVCW-YOLO for Printed Circuit Board Surface Defect Detection |
| title_sort | dvcw yolo for printed circuit board surface defect detection |
| topic | PCB board defect detection YOLOv8n model DVCW-YOLO model C2fCBAM structure WIoU loss function |
| url | https://www.mdpi.com/2076-3417/15/1/327 |
| work_keys_str_mv | AT peishi dvcwyoloforprintedcircuitboardsurfacedefectdetection AT yuyangzhang dvcwyoloforprintedcircuitboardsurfacedefectdetection AT yunqincao dvcwyoloforprintedcircuitboardsurfacedefectdetection AT jiadongsun dvcwyoloforprintedcircuitboardsurfacedefectdetection AT dejichen dvcwyoloforprintedcircuitboardsurfacedefectdetection AT liangkuang dvcwyoloforprintedcircuitboardsurfacedefectdetection |