Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7
Printed Circuit Board (PCB) is a widely used electronic component and plays a critical role in the miniaturization and integration of circuits. However, the detection of PCB defects based on deep learning still encounter difficulties of limited efficiency. In order to address the issues of low speed...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171570 |
| _version_ | 1811676566650880000 |
|---|---|
| author | Chen, Boyuan Dang, Zichen |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Chen, Boyuan Dang, Zichen |
| author_sort | Chen, Boyuan |
| collection | NTU |
| description | Printed Circuit Board (PCB) is a widely used electronic component and plays a critical role in the miniaturization and integration of circuits. However, the detection of PCB defects based on deep learning still encounter difficulties of limited efficiency. In order to address the issues of low speed and accuracy in PCB defect detection process, this paper proposed an innovative PCB defect detection method based on YOLOv7. Firstly, FasterNet was applied as the backbone network structure. With the new partial convolution, the spatial features were extracted more efficiently and the detection speed was improved by reducing redundant computations. Secondly, CBAM attention mechanism was integrated with feature fusion module, which allowed the model to selectively attend to relevant feature channels and spatial locations, thereby enhancing the discriminative ability of the feature representation and improving the accuracy. The experimental results indicated that the proposed model was superior to the traditional network on both PCB defect detection speed and accuracy. (1) The detection speed was increased from 54.3 frames per second to 83.3 frames per second. (2) The mAP0.5 reached 97.5% and mAP0.5:0.95 was increased from 52% to 54.7%. These improvements in speed and accuracy made it a more efficient solution for PCB defect detection. |
| first_indexed | 2024-10-01T02:23:31Z |
| format | Journal Article |
| id | ntu-10356/171570 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:23:31Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1715702023-11-03T15:40:15Z Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 Chen, Boyuan Dang, Zichen School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Feature Extraction Convolution Printed Circuit Board (PCB) is a widely used electronic component and plays a critical role in the miniaturization and integration of circuits. However, the detection of PCB defects based on deep learning still encounter difficulties of limited efficiency. In order to address the issues of low speed and accuracy in PCB defect detection process, this paper proposed an innovative PCB defect detection method based on YOLOv7. Firstly, FasterNet was applied as the backbone network structure. With the new partial convolution, the spatial features were extracted more efficiently and the detection speed was improved by reducing redundant computations. Secondly, CBAM attention mechanism was integrated with feature fusion module, which allowed the model to selectively attend to relevant feature channels and spatial locations, thereby enhancing the discriminative ability of the feature representation and improving the accuracy. The experimental results indicated that the proposed model was superior to the traditional network on both PCB defect detection speed and accuracy. (1) The detection speed was increased from 54.3 frames per second to 83.3 frames per second. (2) The mAP0.5 reached 97.5% and mAP0.5:0.95 was increased from 52% to 54.7%. These improvements in speed and accuracy made it a more efficient solution for PCB defect detection. Published version 2023-10-31T02:22:38Z 2023-10-31T02:22:38Z 2023 Journal Article Chen, B. & Dang, Z. (2023). Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7. IEEE Access, 11, 95092-95103. https://dx.doi.org/10.1109/ACCESS.2023.3311260 2169-3536 https://hdl.handle.net/10356/171570 10.1109/ACCESS.2023.3311260 2-s2.0-85169687463 11 95092 95103 en IEEE Access © 2023 The Author(s). This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Feature Extraction Convolution Chen, Boyuan Dang, Zichen Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title | Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title_full | Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title_fullStr | Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title_full_unstemmed | Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title_short | Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7 |
| title_sort | fast pcb defect detection method based on fasternet backbone network and cbam attention mechanism integrated with feature fusion module in improved yolov7 |
| topic | Engineering::Electrical and electronic engineering Feature Extraction Convolution |
| url | https://hdl.handle.net/10356/171570 |
| work_keys_str_mv | AT chenboyuan fastpcbdefectdetectionmethodbasedonfasternetbackbonenetworkandcbamattentionmechanismintegratedwithfeaturefusionmoduleinimprovedyolov7 AT dangzichen fastpcbdefectdetectionmethodbasedonfasternetbackbonenetworkandcbamattentionmechanismintegratedwithfeaturefusionmoduleinimprovedyolov7 |