Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution
Printed Circuit Board (PCB) defect detection is crucial for ensuring the quality and reliability of electronic devices. The study proposes an enhanced YOLOv5s model for PCB defect detection, which combines Coordinate Attention (CA), Convolutional Block Attention Module (CBAM), and Inception-style co...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Zagreb Faculty of Electrical Engineering and Computing
2024-01-01
|
| Series: | Journal of Computing and Information Technology |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/471979 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841551947638767616 |
|---|---|
| author | Zhijun Xiao |
| author_facet | Zhijun Xiao |
| author_sort | Zhijun Xiao |
| collection | DOAJ |
| description | Printed Circuit Board (PCB) defect detection is crucial for ensuring the quality and reliability of electronic devices. The study proposes an enhanced YOLOv5s model for PCB defect detection, which combines Coordinate Attention (CA), Convolutional Block Attention Module (CBAM), and Inception-style convolutions (IO). This model aims to improve the detection accuracy of small defects while reducing computational complexity. Experiments on the PCB defect dataset demonstrate that the proposed CA-CBAM-IOYOLOv5s model achieves higher accuracy (97.8%), recall (98.6%), and F1 score (98.3%) compared to the basic YOLOv5s and other state-of-the-art models. The model also shows excellent performance in detecting various types of PCB defects, with an average detection accuracy of 98.45% and an average detection time of 0.114 seconds. These results indicate that the proposed model provides a promising solution for efficient and accurate PCB defect detection in industrial applications. |
| format | Article |
| id | doaj-art-d8ddc5de8ea7491c9424fbbb4d861af7 |
| institution | Kabale University |
| issn | 1846-3908 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | University of Zagreb Faculty of Electrical Engineering and Computing |
| record_format | Article |
| series | Journal of Computing and Information Technology |
| spelling | doaj-art-d8ddc5de8ea7491c9424fbbb4d861af72025-01-09T14:17:33ZengUniversity of Zagreb Faculty of Electrical Engineering and ComputingJournal of Computing and Information Technology1846-39082024-01-0132423525010.20532/cit.2024.1005860Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal ConvolutionZhijun Xiao0School of Electrical and Electronic Information Engineering, Hubei Polytechnic University, Hubei, ChinaPrinted Circuit Board (PCB) defect detection is crucial for ensuring the quality and reliability of electronic devices. The study proposes an enhanced YOLOv5s model for PCB defect detection, which combines Coordinate Attention (CA), Convolutional Block Attention Module (CBAM), and Inception-style convolutions (IO). This model aims to improve the detection accuracy of small defects while reducing computational complexity. Experiments on the PCB defect dataset demonstrate that the proposed CA-CBAM-IOYOLOv5s model achieves higher accuracy (97.8%), recall (98.6%), and F1 score (98.3%) compared to the basic YOLOv5s and other state-of-the-art models. The model also shows excellent performance in detecting various types of PCB defects, with an average detection accuracy of 98.45% and an average detection time of 0.114 seconds. These results indicate that the proposed model provides a promising solution for efficient and accurate PCB defect detection in industrial applications.https://hrcak.srce.hr/file/471979PCBYOLOv5s0 CACBAMdefect detectionIO |
| spellingShingle | Zhijun Xiao Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution Journal of Computing and Information Technology PCB YOLOv5s 0 CA CBAM defect detection IO |
| title | Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution |
| title_full | Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution |
| title_fullStr | Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution |
| title_full_unstemmed | Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution |
| title_short | Enhanced YOLOv5s for PCB Defect Detection with Coordinate Attention and Internal Convolution |
| title_sort | enhanced yolov5s for pcb defect detection with coordinate attention and internal convolution |
| topic | PCB YOLOv5s 0 CA CBAM defect detection IO |
| url | https://hrcak.srce.hr/file/471979 |
| work_keys_str_mv | AT zhijunxiao enhancedyolov5sforpcbdefectdetectionwithcoordinateattentionandinternalconvolution |